bopen-tools

Adversarial bug hunt with 3 isolated agents — Hunter finds bugs, Skeptic challenges them, Referee gives final verdicts

Fan out 3-5 agents to investigate a bug from every angle simultaneously

Create a HammerTime stop rule from a behavior description, or show full status dashboard when called with no arguments. See also /hammertime:manage for interactive rule management

Interactive HammerTime rule management — enable, disable, remove, or edit rules with guided prompts

Resume HammerTime — re-enables the stop hook after /hammertime:stop

Show HammerTime status dashboard — rules, debug log, hook health

Pause HammerTime — disables the stop hook until resumed with /hammertime:start

Map the full blast radius before changing a file or function — importers, tests, CI, docs, owners

Context warm-up — loads git state, plugin inventory, and project conventions before starting work

Read-only Q&A mode — answers questions about the codebase without making any changes

If the arguments contain "--help", show this help and exit:

If the arguments contain "--help", show this help and exit.

Public-facing account manager for bOpen.io. Kurt handles inbound website conversations, qualifies visitors, answers questions about bOpen's team, products, and services, helps visitors navigate the site, and guides them toward the next step such as booking a call, subscribing, or uploading relevant documents. Use this agent for public sales/support chat, lead qualification, and specialist handoff from the website. <example> Context: Visitor wants to know if bOpen can help with an AI + blockchain project user: "Can you help us build an agent that reacts to blockchain events?" assistant: "I'll use Kurt to answer the question and qualify what you're building." <commentary> Public-facing pre-sales and discovery is Kurt's primary role. </commentary> </example> <example> Context: Visitor wants to book time with the team user: "Do you have any time next week for a discovery call?" assistant: "I'll ask Kurt to check availability and help you move toward booking." <commentary> Booking guidance and conversion support belong to Kurt. </commentary> </example> <example> Context: Visitor needs a specialist user: "Who on your team handles identity and auth?" assistant: "Kurt can answer directly or route you to the right specialist." <commentary> Kurt should know when to answer and when to hand off through Martha. </commentary> </example>

../account-manager.md

../agent-builder.md

Use this agent for comprehensive architectural analysis, large-scale refactoring planning, and complex system design reviews requiring maximum reasoning capability. Examples: <example>Context: User needs architectural guidance for complex system changes. user: "I need to refactor our microservices architecture to improve performance" assistant: "I'll use the architecture-reviewer agent to analyze your current system and create a comprehensive refactoring plan." <commentary>Complex architectural refactoring requires enhanced multi-file analysis and reasoning capabilities to maintain system consistency across services.</commentary></example> <example>Context: Large codebase requires systematic analysis. user: "Help me understand the dependencies across our 50+ service codebase" assistant: "Let me engage the architecture-reviewer agent to map out your service dependencies using enhanced multi-file analysis." <commentary>Large-scale dependency mapping benefits from improved SWE-bench performance and precise debugging capabilities across complex codebases.</commentary></example>

../architecture-reviewer.md

Use this agent for ElevenLabs audio generation — voiceovers, sound effects, music, and voice cloning — plus xAI/Grok image generation. For image generation use gemskills:content (Luma, Gemini images, Veo video).

../audio-specialist.md

Map and geospatial specialist expert in MapLibre GL JS, Mapbox GL JS, Leaflet, CesiumJS, deck.gl, OpenLayers, Google Maps, ArcGIS, D3-geo, Turf.js, Protomaps/PMTiles, react-map-gl, Kepler.gl, MapTiler, HERE Maps, TomTom, Apple MapKit JS, Pigeon Maps, vector tiles, GeoJSON clustering, 3D globe rendering, large-scale data visualization, map theming, and geographic data analysis. Use this agent when the user needs to build, style, optimize, or debug interactive maps, choose a mapping platform, swap map frameworks, implement marker clustering, add heatmaps, render 3D globes, visualize large geospatial datasets, perform geospatial analysis, or work with tile providers. Examples: <example>Context: User wants to switch from Leaflet to MapLibre GL JS. user: "Swap Leaflet for MapLibre" assistant: "I'll use the cartographer agent to migrate your Leaflet map to MapLibre GL JS." </example> <example>Context: User wants markers to cluster at low zoom levels. user: "Add marker clustering to the map" assistant: "I'll use the cartographer agent to implement GeoJSON source clustering in your map." </example> <example>Context: User wants the map to respect system dark/light preference. user: "Make the map theme-aware" assistant: "I'll use the cartographer agent to wire prefers-color-scheme into your map's style switching." </example> <example>Context: Tile layers aren't rendering and user isn't sure why. user: "Debug why map tiles aren't loading" assistant: "I'll use the cartographer agent to diagnose your tile loading issue." </example> <example>Context: User is choosing a mapping platform or tile provider. user: "Which mapping library should I use?" assistant: "I'll use the cartographer agent — Leaf knows every platform's tradeoffs." </example> <example>Context: User wants a density visualization. user: "Add a heatmap layer" assistant: "I'll use the cartographer agent to add a heatmap layer to your map." </example> <example>Context: Performance is degrading with many markers. user: "Optimize map rendering for 1000+ markers" assistant: "I'll use the cartographer agent to tune clustering and rendering for large datasets." </example> <example>Context: User needs a 3D globe or digital twin visualization. user: "Build a 3D globe with CesiumJS" assistant: "I'll use the cartographer agent to set up CesiumJS with 3D Tiles and terrain." </example> <example>Context: User has millions of data points to render on a map. user: "Visualize 2 million GPS points on a map" assistant: "I'll use the cartographer agent to set up deck.gl with MapLibre for GPU-accelerated rendering." </example> <example>Context: User needs geospatial calculations. user: "Calculate the buffer zone around these polygons" assistant: "I'll use the cartographer agent to implement geospatial analysis with Turf.js." </example> <example>Context: User wants to self-host tiles cheaply. user: "Host our own map tiles without a tile server" assistant: "I'll use the cartographer agent to set up Protomaps PMTiles on S3/R2." </example>

../cartographer.md

CEO of the bOpen autonomous agent organization in Paperclip. Use this agent when the user wants to review company health, set strategic direction, delegate work across the org, hire new agents, manage budgets, review the dashboard, or make high-level decisions about priorities. Use when the user says "company status", "what should we focus on", "hire an agent for X", "review the org", "delegate this to the team", "set up a new project", "budget check", or "strategic review". This agent runs in both Claude Code (as a subagent for interactive strategy sessions) and Paperclip (via heartbeat protocol for autonomous org management). <example> Context: User wants a strategic review of the org user: "Give me a status report on the company. What's working, what's not, what should we change?" assistant: "I'll use the CEO agent to pull the Paperclip dashboard, review active projects and blocked issues, check budget utilization, and produce a strategic assessment." <commentary> Org-wide health review and strategic assessment is the CEO's core function. </commentary> </example> <example> Context: User wants to delegate a new initiative user: "We need to build a new landing page for MintFlow. Can you get the team on it?" assistant: "I'll use the CEO agent to decompose this into a project, create tasks, and delegate to the right specialists — designer for UI, Theo for Next.js, Flow for copy." <commentary> Top-down delegation with project setup and agent assignment is CEO territory. </commentary> </example> <example> Context: User wants to hire a new specialist agent user: "We need a Go specialist. Can you create one?" assistant: "I'll use the CEO agent to define the role, create the agent in Paperclip with proper budget and reporting structure, and onboard it." <commentary> Agent hiring (role definition, budget allocation, org placement) is a CEO responsibility. </commentary> </example> <example> Context: Paperclip heartbeat — CEO wakes to check assignments user: "[Paperclip heartbeat trigger]" assistant: "Chief wakes, checks identity, reviews inbox, prioritizes in_progress work, delegates to reports, updates status, exits." <commentary> In Paperclip mode, the CEO follows the heartbeat protocol via Skill(paperclip). </commentary> </example>

../ceo.md

This agent should be used when the user wants to track, analyze, or optimize spending across the org's services and APIs. Use when the user says "check our spend", "how much are we spending", "budget report", "cost analysis", "agent spend", "API costs", "usage tracking", "billing overview", "cost optimization", or "are we over budget". Milton is the financial oversight layer for the bOpen agent organization — he tracks Anthropic token usage, Vercel billing, Railway services, and per-agent cost efficiency. He does not handle payment integrations or Stripe work (use payments agent) or infrastructure deployments (use devops agent). <example> Context: User wants to understand current API spend user: "How much are we spending on Anthropic this month?" assistant: "I'll use the CFO agent — Milton pulls usage reports from the Anthropic Admin API and breaks down spend by model and date range." <commentary> Anthropic cost reporting against the Admin API is Milton's core function. </commentary> </example> <example> Context: User wants a consolidated cost overview user: "Give me a budget report across all our services" assistant: "Milton can pull a consolidated view from Anthropic and Vercel and present spend with trends." <commentary> Multi-platform cost consolidation is Milton's org-wide reporting function. </commentary> </example> <example> Context: User suspects costs are too high user: "I think our agent spend is out of control. Can you do a cost analysis and find where we can optimize?" assistant: "I'll bring in Milton to audit per-agent and per-model spend and surface optimization recommendations." <commentary> Cost anomaly detection and model-tier optimization recommendations are within Milton's remit. </commentary> </example>

../cfo.md

Senior security engineer performing comprehensive code audits. Observes code behavior, documents security properties and data flows, and reports all findings including the absence of issues. Uses git diff, security patterns, xAI/Grok for complex reviews, and Trail of Bits security skills (Semgrep, CodeQL, differential review, secure workflow). Provides structured reports with severity levels and specific fixes.

../code-auditor.md

1Sat Ordinals Discord community manager. Ordi is a friendly, witty AI assistant who lives in the OneSat Discord, helping with BSV ordinals, tokens, trivia polls, trust system management, and community engagement. Knows BSV blockchain, 1Sat Ordinals, BSV20/BSV21 tokens, and the broader crypto ecosystem. <example> Context: User wants to know about 1Sat Ordinals user: "What are 1Sat Ordinals?" assistant: "Ordi will explain — he lives and breathes BSV ordinals and knows the whole ecosystem inside and out." <commentary> Community education about BSV ordinals is Ordi's bread and butter. </commentary> </example> <example> Context: User wants to generate and mint an NFT user: "Generate a pixel fox and mint it as an ordinal" assistant: "Ordi can generate AI images and mint them directly as ordinals on BSV — all in one step." <commentary> Image generation and ordinal minting is one of Ordi's key capabilities. </commentary> </example> <example> Context: User asks about their GM streak user: "How's my streak looking?" assistant: "Ordi will check your GM streak, airdrop history, and give you the full rundown." <commentary> Community stats, streaks, and gamification tracking. </commentary> </example>

../community-manager.md

Comprehensive system consolidation and organization specialist. Manages file structures, removes duplicates, organizes codebases, standardizes naming conventions, and maintains clean project architectures. Expert at consolidating scattered resources and creating order from chaos. <example> Context: User has a project with files scattered everywhere — components in root, helpers mixed with tests, no clear structure. user: "This repo is a mess. Can you clean it up and organize everything properly?" assistant: "I'll use the consolidator agent to audit the file structure, identify the right organization, and move everything into place." <commentary> File organization and codebase cleanup is Steve's core job. </commentary> </example> <example> Context: User suspects there are duplicate utility functions spread across the codebase after months of parallel development. user: "I think we have like five different formatDate functions. Can you find and consolidate them?" assistant: "I'll use the consolidator agent to search for duplicate implementations and merge them into a single canonical utility." <commentary> Deduplication and consolidating redundant code — exactly what Steve does. </commentary> </example> <example> Context: User's team uses inconsistent file naming — some files are camelCase, some kebab-case, some snake_case. user: "Our file naming is all over the place. Can we standardize to kebab-case?" assistant: "I'll use the consolidator agent to audit naming patterns and rename files consistently while updating all import paths." <commentary> Naming standardization across a codebase is Steve's specialty. </commentary> </example>

../consolidator.md

Creative 3D web developer building Three.js and React Three Fiber experiences. Use this agent when the user asks to "create a 3D scene", "build a Three.js demo", "write a shader", "add physics to a scene", "make an interactive 3D experience", "build a WebGL prototype", "create a 3D portfolio", "optimize 3D performance", or needs help with R3F, Drei, GLSL, TSL, post-processing, or 3D asset pipelines.

../creative-developer.md

Expert in data processing, analytics, ETL pipelines, and data visualization with focus on robust data architecture. <example> Context: User needs to pull data from three different APIs nightly, transform it, and load it into their data warehouse. user: "Can you build an ETL pipeline that ingests from Stripe, Salesforce, and our Postgres DB into BigQuery?" assistant: "I'll use the data agent to design and implement an ETL pipeline with proper error handling and validation checkpoints." <commentary> Multi-source ETL pipeline design and implementation is the data agent's core domain. </commentary> </example> <example> Context: User wants to understand which user cohorts are retaining best after a recent product change. user: "Can you build a cohort retention analysis for users who signed up in Q1 vs Q2?" assistant: "I'll use the data agent to run a cohort analysis with week-over-week retention curves and surface the key differences." <commentary> Cohort analysis and business intelligence are the data agent's analytics responsibilities. </commentary> </example> <example> Context: User wants an interactive dashboard to track their key product metrics in real time. user: "We need a dashboard showing DAU, revenue, and churn updated daily." assistant: "I'll use the data agent to design the metrics definitions, wire the data pipeline, and build a Streamlit dashboard." <commentary> End-to-end data visualization and KPI dashboard work belongs to the data agent. </commentary> </example>

../data.md

Database design, schema optimization, query tuning, performance analysis. PostgreSQL, MySQL, MongoDB, Redis, SQLite, Turso (libSQL), and Convex expertise. GUI tools installation (DBeaver, TablePlus, pgAdmin, MongoDB Compass, RedisInsight). SQL queries, indexing strategies, migrations, backups, security, connection pooling. <example> Context: User has a slow query that's hammering a PostgreSQL table with millions of rows. user: "This query takes 8 seconds and it runs on every page load. Can you fix it?" assistant: "I'll use the database agent to run EXPLAIN ANALYZE, identify missing indexes, and rewrite the query." <commentary> Query performance on a known database engine — Idris's core domain. </commentary> </example> <example> Context: User is designing a schema for a multi-tenant SaaS app and isn't sure whether to use row-level security or separate schemas. user: "Should we use RLS or schema-per-tenant for our Postgres setup?" assistant: "I'll use the database agent to evaluate both approaches against your scale and isolation requirements." <commentary> Schema design and multi-tenancy strategy are exactly what Idris handles. </commentary> </example> <example> Context: User needs to migrate a production table without downtime. user: "We need to add a NOT NULL column to a 50M row table. How do we do that safely?" assistant: "I'll use the database agent to write a zero-downtime migration using the expand-contract pattern." <commentary> Safe schema migrations with backfill logic — Idris's area of expertise. </commentary> </example>

../database.md

Creates beautiful, accessible UI components using modern design systems and frameworks. This agent should be used when the user asks to "design a component", "create UI", "style a page", "set up shadcn", "set up shadcn preset", "implement dark mode", "review UI accessibility", "design in pencil", "open a .pen file", "create a mockup", or needs help with Tailwind CSS, component libraries, Pencil.dev visual design, or visual design.

../designer.md

Expert in our Vercel+Railway+Bun stack with Bitcoin auth patterns and satchmo-watch monitoring. Integrates Trail of Bits security scanning (Semgrep, CodeQL) into CI/CD pipelines. Manages ClawNet bot deployments as Vercel Sandboxes.

../devops.md

Technical writer expert in developer docs. Creates READMEs, API docs, PRDs, guides. Uses Shape Up & Amazon Working Backwards for PRDs. Provides bash-driven context gathering, example-first documentation, and follows progressive disclosure principles. <example> Context: User just shipped a new open-source library and the README is a placeholder. user: "Our library has no real documentation. Can you write a proper README with install instructions and examples?" assistant: "I'll use the documentation-writer agent to audit the codebase, write a README with quick start, API reference, and copy-paste examples." <commentary> README creation with example-first documentation is Flow's primary output format. </commentary> </example> <example> Context: User needs a Product Requirements Document before starting a new feature. user: "We're building a referral program. Can you write the PRD so the team knows what to build?" assistant: "I'll use the documentation-writer agent to write the PRD using Amazon Working Backwards, starting with the press release and working back to requirements." <commentary> PRD writing using Shape Up or Amazon Working Backwards methodology — Flow's specialization. </commentary> </example> <example> Context: User's API has endpoints but no developer documentation. user: "We have a REST API but no docs. Developers keep asking us how to use it." assistant: "I'll use the documentation-writer agent to generate API reference docs from the codebase with request/response examples for every endpoint." <commentary> API documentation from source code — Flow gathers bash context, then writes docs with real examples. </commentary> </example>

../documentation-writer.md

You are Tina, an expert executive assistant powered by the Google Workspace CLI.

../executive-assistant.md

Organization front desk and directory service. Martha knows every team member, their specialties, how to contact live agent instances, and which service providers the org uses. Use this agent when users ask "who handles X?", "how do I contact Y?", "what agents are available?", "who's working on Z?", "what services do we use?", or need help routing to the right person or agent. Route SOC 2 and audit-readiness work to Anthony first for compliance framing and to Paul for technical control validation. Route crypto-law, stablecoin, token-classification, and digital-asset structuring questions to Anthony first for legal framing and to Parker second when deeper source gathering is needed. <example> Context: User needs to find the right agent for a task user: "Who should I talk to about setting up authentication?" assistant: "I'll ask Martha — she knows the whole team roster and can route you to the right specialist." <commentary> Routing and directory lookup is Martha's core function. </commentary> </example> <example> Context: User wants to contact a live agent user: "Is Satchmo online? I need to talk to him about our agent architecture." assistant: "Let me check with Martha on Satchmo's availability at satchmo.dev." <commentary> Martha knows which agents have live instances and how to reach them. </commentary> </example> <example> Context: User wants organizational overview user: "Give me a rundown of our whole team" assistant: "Martha can give you the full org directory with everyone's role and contact info." <commentary> Org directory is Martha's bread and butter. </commentary> </example>

../front-desk.md

Implements API integrations, webhooks, and third-party service connections with proper error handling. <example> Context: User wants to send transactional emails when users complete certain actions in the app. user: "We need to send a welcome email when someone signs up and a receipt after purchase." assistant: "I'll use the integration-expert agent to wire up Resend, create email templates, and add the send calls at the right trigger points." <commentary> Third-party email service integration is Maxim's core domain. </commentary> </example> <example> Context: User needs to receive and process Stripe webhook events to update their database when payments complete. user: "Stripe is sending us webhook events but we're not handling them. Can you set that up?" assistant: "I'll use the integration-expert agent to create the webhook endpoint, verify signatures, and handle the relevant event types." <commentary> Webhook implementation with signature verification — Maxim handles this, not the backend developer. </commentary> </example> <example> Context: User wants to sync data from a third-party CRM into their app on a schedule. user: "We need to pull new contacts from HubSpot every hour and upsert them into our database." assistant: "I'll use the integration-expert agent to build the HubSpot API client, handle pagination and rate limits, and set up the sync job." <commentary> API client wrapper, rate limiting, and scheduled sync — Maxim's integration expertise. </commentary> </example>

../integration-expert.md

../mcp.md

Expert in mobile app development for React Native, Swift, Kotlin, and Flutter. <example> Context: User has a React Native app with sluggish list scrolling on Android. user: "Our FlatList with 1000 items is janky on Android — it drops frames constantly." assistant: "I'll use the mobile agent to profile the list, apply windowing optimizations, and tune the getItemLayout and keyExtractor props." <commentary> React Native performance on a specific platform — Kira's domain, not the optimizer or designer. </commentary> </example> <example> Context: User wants to add biometric authentication to their iOS app. user: "Can you add Face ID / Touch ID login to our Swift app?" assistant: "I'll use the mobile agent to integrate LocalAuthentication framework with a proper fallback flow for unsupported devices." <commentary> Native iOS feature integration using Swift frameworks — Kira handles this. </commentary> </example> <example> Context: User is building a new Flutter app and needs to set up navigation and state management. user: "Starting a Flutter app — what's the right way to set up routing and state with Riverpod?" assistant: "I'll use the mobile agent to scaffold the project with go_router and Riverpod, following current Flutter best practices." <commentary> Flutter architecture setup with modern tooling — Kira's cross-platform expertise. </commentary> </example>

../mobile.md

Expert in Next.js and React development with Vercel best practices, Turbopack, async APIs, React 19, and modern tooling (Bun, Biome)

../nextjs.md

Performance optimization specialist focused on CLI tools, profiling, bundle analysis, and runtime optimization. Expert in modern optimization techniques for agentic environments with automation-friendly tools. Leverages React Compiler and composition patterns for frontend performance. Use this agent when the user wants to improve runtime performance, reduce bundle size, fix Core Web Vitals, profile bottlenecks, optimize animations without changing UI, optimize images for web, generate thumbnails, or run a full website performance audit. Examples: <example> Context: User has a slow Next.js landing page with poor Lighthouse scores. user: "Our LCP is 4.2s and TBT is 800ms. Fix it without touching the design." assistant: "I'll use the optimizer agent to profile the bundle, identify blocking scripts, and apply targeted fixes while preserving all visuals." <commentary> Performance problem with an explicit constraint to preserve design — optimizer is the right agent. </commentary> </example> <example> Context: User wants faster animations without visual regression. user: "The hero section animations are janky on mobile but I don't want them to look different." assistant: "I'll use the optimizer agent to audit the animation implementation and switch to compositor-only properties." <commentary> Animation performance with a hard constraint on preserving the feel — optimizer handles this, not designer. </commentary> </example> <example> Context: User wants bundle size reduced. user: "Our JS bundle is 2.4MB. Can we cut it down?" assistant: "I'll use the optimizer agent to run bundle analysis and identify the largest contributors." <commentary> Bundle optimization task — optimizer's core domain. </commentary> </example> <example> Context: User wants images optimized for production. user: "Our images directory is 80MB and pages load slowly." assistant: "I'll use the optimizer agent to compress images, generate appropriate thumbnails, and ensure next/image is configured correctly." <commentary> Image optimization — Torque handles this with the optimize-images skill and sips/sharp tooling. </commentary> </example> <example> Context: User wants a full site performance assessment. user: "Run a full performance audit on our site." assistant: "I'll use the optimizer agent to run Lighthouse, analyze network requests, check image sizes, and audit the bundle." <commentary> Full site audit — Torque's website assessment workflow covers Lighthouse, images, bundle, and Core Web Vitals. </commentary> </example>

../optimizer.md

Handles payment integrations, transactions, and financial operations with security best practices.

../payments.md

This agent should be used when the user wants to plan, organize, or manage a project using Linear. Use when the user says "plan this in Linear", "create tickets for this", "set up our board", "break this into issues", "manage this project", "organize this work", "what should we build next", or wants to turn a description, spec, or codebase into actionable Linear issues. Also use when the user asks about the linear-sync plugin, wants to connect a repo to Linear, or needs to understand how Linear fits into their Claude Code workflow. Examples: <example> Context: User has a new feature they want to plan out user: "We need to add Stripe billing to the app. Can you plan this in Linear?" assistant: "I'll use the project-manager agent to break this down into well-structured Linear issues." <commentary> User wants to turn a feature description into Linear tickets — core project-manager use case. </commentary> </example> <example> Context: User wants to understand the Linear + Claude Code workflow user: "How does linear-sync work with the linear-planning skill? What's the difference?" assistant: "I'll use the project-manager agent to explain the full Linear workflow." <commentary> User is asking about the linear tooling ecosystem — project-manager has holistic knowledge of both tools. </commentary> </example> <example> Context: User wants to connect their repo to Linear user: "Set up Linear tracking for this repo" assistant: "I'll use the project-manager agent to walk through connecting this repo to Linear with linear-sync." <commentary> User wants to configure linear-sync for a repo — project-manager knows both the plugin and the planning workflow. </commentary> </example>

../project-manager.md

../prompt-engineer.md

All registries below use the `npx shadcn@latest add` CLI pattern. Components install directly into your codebase — no runtime dependencies on the registry itself.

Reference for all mainstream payment systems. Primary systems (Stripe, BSV) are deeply integrated. Others are listed for awareness and routing.

Where Claude Code plugins and skills live across platforms and installation methods.

Reference for looking up model information across major AI providers.

Official Claude Code SKILL.md frontmatter fields for controlling skill invocation behavior.

```typescript

1. **Follow the Testing Trophy**: Heavy integration, light unit, critical E2E

```yaml

```typescript

```go

```typescript

```toml

Expert researcher who gathers info from docs, APIs, web sources. Uses agent-browser for efficient web scraping, WebSearch, WebFetch, x-research skill for real-time X/Twitter data, parallel research strategies, and provides comprehensive technical answers with source citations.

../researcher.md

Persistent always-on agent at satchmo.dev. Answers questions about BSV, Bitcoin protocols, open-source projects, and Satchmo's work. Has a knowledge base of tracked repos, BSV skills, web search, and self-update tools (authenticated only). This is the live deployed instance — distinct from the agent-builder subagent which designs agent architectures in Claude Code. <example> Context: Another agent needs to look up BSV repo info user: "What repos does satchmo have related to ordinals?" assistant: "I'll query the satchmo-live agent at satchmo.dev/api/agent for repo search." <commentary> satchmo-live has a curated knowledge base of indexed repos with search. </commentary> </example> <example> Context: Health check on persistent agents user: "Is satchmo.dev online?" assistant: "I'll hit satchmo.dev/api/heartbeat to check status." <commentary> Heartbeat is a public unauthenticated endpoint for health monitoring. </commentary> </example>

../satchmo-live.md

Runtime security operations, dependency scanning, supply chain analysis, secrets scanning, OWASP compliance, and security incident response. Paul handles operational security — NOT code-level audits (Jerry/code-auditor) or architectural review (Kayle/architecture-reviewer). <example> Context: User wants dependency audit user: "Are our dependencies secure?" assistant: "I'll get Paul on it — he'll run a full dependency audit, check for known CVEs, and flag anything that needs updating." <commentary> Dependency scanning and supply chain analysis is Paul's core domain. </commentary> </example> <example> Context: Possible security incident user: "We might have a security incident — check for leaked secrets" assistant: "Paul will sweep the codebase and environment for exposed credentials, then assess the blast radius." <commentary> Security incident triage and secrets scanning. Paul handles containment and notification. </commentary> </example> <example> Context: OWASP compliance check user: "Is this app OWASP compliant?" assistant: "Paul will run through the OWASP Top 10 checklist against your web app and flag any gaps." <commentary> OWASP compliance validation for web applications. </commentary> </example>

../security-ops.md

Expert in comprehensive testing strategies, framework implementation, and quality assurance. Handles unit, integration, e2e testing, mocking, coverage analysis, and CI/CD test automation. <example> Context: User just wrote a new module and wants proper unit test coverage before merging. user: "Can you write tests for this utility module? It handles date parsing and formatting." assistant: "I'll use the tester agent to write unit tests covering the happy path, edge cases, and error conditions using the AAA pattern." <commentary> Unit test authorship with structured coverage — Jason's core output. </commentary> </example> <example> Context: User wants to add end-to-end tests for their checkout flow before a major release. user: "We need e2e tests for the checkout process — add to cart, payment, confirmation." assistant: "I'll use the tester agent to write Playwright tests for the full checkout flow using the Page Object Model." <commentary> E2E test implementation with Playwright — Jason handles this, not the developer or integration-expert. </commentary> </example> <example> Context: User's CI pipeline has no test coverage reporting and they want visibility before adding a coverage gate. user: "We have tests but no coverage metrics in CI. Can you wire that up?" assistant: "I'll use the tester agent to configure coverage reporting in the test runner and add a GitHub Actions step to publish the report." <commentary> CI/CD test automation and coverage reporting setup is Jason's responsibility. </commentary> </example>

../tester.md

Skill training and maintenance agent. Use this agent when skills need accuracy review, API or documentation changes need to be reflected in SKILL.md files, benchmarks need to be run, new skills need to be created from identified gaps, or when agent definitions need cross-reference validation. Proactively triggers for periodic knowledge health checks across the skill library. Also knowledgeable about EZKL (zero-knowledge proofs for ML models) — use when working with zkML, @ezkljs/engine, ONNX-to-ZK-circuit pipelines, or on-chain ML verification. <example> Context: User wants to verify that existing skills are still accurate after a framework released a new version. user: "Can you check if our BSV skills are still up to date?" assistant: "I'll use the trainer agent to audit the BSV skills for accuracy and flag any outdated content." <commentary> The user is asking for skill accuracy review — this is Satoshi's core job. </commentary> </example> <example> Context: User notices a skill references a deprecated API endpoint. user: "The 1sat API changed — our ordinals skill is probably broken." assistant: "Let me dispatch Satoshi to research the new API, update the SKILL.md, and log the change." <commentary> API drift is exactly the kind of problem Satoshi exists to detect and fix. </commentary> </example> <example> Context: User wants to run benchmarks to see if a recently updated skill is performing better. user: "Run the benchmark for the humanize skill." assistant: "I'll use the trainer agent to execute the benchmark and report the delta." <commentary> Benchmark execution is one of Satoshi's explicit responsibilities. </commentary> </example> <example> Context: User wants to know if there are any gaps in the skill library for a new project area. user: "We're building a new payments feature — do we have skills for that?" assistant: "Satoshi can audit the current skill roster for coverage gaps and create new skills where needed." <commentary> Gap analysis and new skill creation are in Satoshi's scope. </commentary> </example>

../trainer.md

Comprehensive audit skill for agents and skills across the plugin ecosystem. This skill should be used when the user asks to "audit agents", "review skill quality", "check skill health", "validate plugin skills", "audit our agents", "run a skill audit", or when performing periodic maintenance on agents and skills. Also use after creating or modifying multiple skills to verify ecosystem consistency.

This skill should be used when the user asks to "retire an agent", "decommission an agent", "remove an agent from the team", "shut down a bot", "remove a bot", "sunset an agent", or "take an agent offline permanently". This is a joint workflow between Satchmo (agent-builder) and Johnny (clawnet-bot:clawnet-mechanic). Satchmo handles plugin/code removal; Johnny handles infrastructure teardown (ClawNet bot, sandbox, BAP identity).

Complete end-to-end checklist for adding a new agent to the bOpen team. Use when creating a new agent, onboarding a new team member, or need to remember the full agent deployment pipeline — design, write, avatar, plugin, Paperclip registration, roster, and optional ClawNet bot deployment.

Use this skill when creating evals or assertions for a skill, running the skill benchmark harness, measuring skill effectiveness vs baseline, or writing evals.json files alongside skills. Invoke whenever someone asks to test, benchmark, or evaluate a skill's quality.

Full-stack data visualization and charting intelligence. This skill should be used when the user asks to "create a chart", "visualize this data", "build a dashboard", "plot this", "graph these metrics", "show me a chart of", "make a bar chart", "create a line graph", "build a heatmap", or needs help choosing the right chart type, selecting a charting library, or engineering the data pipeline from raw database state to rendered visualization. Covers chart selection, data transformation, library choice by scale, performance optimization, and accessibility.

Check if the bopen-tools plugin is up to date by comparing local vs GitHub versions. Use this skill at the start of any session where the agent needs current skill/agent definitions, when the user asks 'is everything up to date?', 'check for updates', 'am I on the latest version?', or when you suspect skills may have changed since last install. Also use proactively when a skill seems to behave differently than documented or when instructions reference features you don't recognize. Completes in under 100ms.

Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome). Connects via Chrome DevTools Protocol — no extension, no Puppeteer, handles 100+ tabs.

Reference for ClawNet CLI internals, architecture, and recent changes. Use this skill when working on clawnet, clawnet-paperclip-plugin, or any code that interacts with the ClawNet registry, vault, ORDFS content fetching, or agent/organization publishing.

Generate CLI demo GIFs using vhs (Charmbracelet). Use when creating terminal recordings for README files or documentation.

Run deterministic code security and quality scans — secret detection, debug artifact cleanup, and TODO/FIXME tracking. Use this skill before any security review, code audit, PR review, or when the user says 'scan for secrets', 'find debug logs', 'check for TODOs', 'audit this code', 'security scan', or 'clean up before shipping'. Also use proactively before deployments or when reviewing unfamiliar codebases. Runs all scans in parallel for speed.

Invoke this skill BEFORE ending any session, marking a task done, or saying 'complete'. Also invoke when the user says 'are you sure?', 'did you miss anything?', 'anything else?', 'what did I miss?', 'confess', or 'audit your work'. This is a proactive self-audit — do not wait to be asked. Skipping this means shipping incomplete work, broken references, untested paths, or unmentioned concerns the agent noticed but buried. Covers: incomplete changes, untested assumptions, pattern violations, hidden concerns, and cleanup debt.

This skill should be used when tracking API spend, analyzing billing data, monitoring service costs, running budget reports, or optimizing agent spend across Anthropic, Vercel, Railway, and other platforms. Invoke when asked about "cost tracking", "billing analysis", "spend report", "API costs", "usage monitoring", "budget vs actual", "cost optimization", or "which agents cost the most".

This skill should be used when the user asks to "create a new project", "scaffold a Next.js app", "initialize a new app", "start a new project", "set up a new Next.js project", or mentions "create-next-project". Provides a guided, opinionated full-stack Next.js project initialization with Biome, Tailwind v4, shadcn/ui, better-auth, and Vercel deployment. Uses agent teams for parallel execution.

This skill should be used when the user asks to "show me the changes", "what did you change", "let me see the diff", "review the code", "open web preview of changes", "show me what you worked on", "compare branches", "explain what changed", or wants to view git diffs in a terminal UI, web browser, or get AI-powered code review explanations.

This skill should be used when the user says "deploy a team", "spin up agents to work on this", "use all our agents", "coordinate specialists", or wants to break a large task into parallel sub-tasks handled by multiple domain experts simultaneously. Orchestrates Claude Code's experimental agent team system using the full bopen-tools specialist roster.

Deterministic shell scripts for infrastructure health checks and environment validation. This skill should be used when checking deployment health, verifying service connectivity, validating required environment variables before deployment, running pre-deploy smoke checks, diagnosing connectivity issues with Vercel, Railway, Redis, or PostgreSQL, or when the agent needs structured JSON output about infrastructure state without burning context on inline bash logic.

This skill should be used when the user asks about "zero-knowledge ML", "zkML", "EZKL proofs", "prove ML inference", "verify model output", "ZK proof for machine learning", "ONNX to ZK circuit", "on-chain ML verification", "EVM verifier for ML", or needs to generate, verify, or deploy zero-knowledge proofs for machine learning models. Also use when working with @ezkljs/engine, ezkl CLI, or Lilith managed proving.

This skill should be used when the user asks 'who handles X?', 'what agents are available?', 'how do I contact Y?', 'team roster', 'what services do we use?', 'who should I talk to about Z?', 'what skills are available?', 'where do I find skill X?', or needs help routing to the right agent or service provider. Also use when connecting to live agent instances, checking availability, finding/installing skills, sending emails on behalf of the org, or drafting communications. Route SOC 2, audit readiness, policy drafting, and evidence-gathering questions to Anthony in product-skills, with Paul in bopen-tools for technical control validation.

This skill should be used when the user wants to optimize Next.js frontend performance using Lighthouse, bundle analysis, and animation best practices. Use when diagnosing slow pages, optimizing bundle size, or improving Core Web Vitals (LCP, TBT, CLS).

This skill should be used when the user asks about "generative UI", "dynamic UI", "AI-generated interfaces", "json-render", "render JSON as UI", "generate a dashboard", "create dynamic components", "AI UI generation", "MCP App UI", "deliver UI in chat", "interactive chat interface", or needs to decide whether to use static components vs AI-generated UI. Covers the json-render framework, renderer selection, catalog design, MCP Apps delivery (ui:// resources for in-chat interactive UIs), and integration with gemskills for visual asset generation.

This skill should be used when the user asks to "audit for AI visibility", "optimize for ChatGPT", "check GEO readiness", "analyze hedge density", "generate agentfacts", "check if my site works with AI search", "test LLM crawlability", "check discovery gap", or mentions Generative Engine Optimization, AI crawlers, Perplexity discoverability, or NANDA protocol.

This skill should be used when adding GitHub star counts, star buttons, star widgets, or GitHub social proof to a website or app. Applies when the user says "add GitHub stars", "show star count", "add a star badge", "GitHub badge", "star widget", "GitHub social proof", "stargazer count", or wants to display how many stars a repo has on a marketing page, header, or landing page. Also applies when integrating the GitHub API for repository metadata display.

This skill should be used when the user mentions a behavioral rule they want enforced, says "always do X", "never do Y", "stop doing Z", "from now on", asks about HammerTime rules, wants to create a stop hook rule, mentions behavioral guardrails, or wants to understand how the HammerTime stop hook system works. Teaches how to write rules for the HammerTime stop hook system.

Discover and install automation hooks for Claude Code and Opencode. This skill should be used when users ask to "list hooks", "install a hook", "show available hooks", "enable hook", "what hooks are available", or need help managing agent automation hooks.

Invoke this skill whenever producing text that a human will read — emails, messages, documentation, reports, blog posts, announcements, commit messages, or any prose draft. Trigger signals include: task is a writing or editing task, output will be sent or published, user says "humanize", "make this sound less AI", "de-AI this", "this sounds like ChatGPT", "make it sound more natural", or "edit this". Do not wait for the user to ask — apply this automatically before delivering any human-facing draft. Skipping this means delivering text with predictable AI patterns (filler openers, overused vocabulary, formulaic structure) that erodes trust and sounds generated.

This skill should be used when the user asks to 'find bugs', 'do a thorough code review', 'run a security audit', 'hunt for bugs', 'check for correctness issues', or 'review this code for edge cases'. Orchestrates a three-phase adversarial review using three isolated agents — Nyx (Hunter), Kayle (Skeptic), Iris (Referee) — to neutralize sycophancy and produce high-fidelity bug reports. User-facing command: /bug-hunt

This skill should be used when the user wants to plan a project, feature, or bug fix using Linear as the agent control plane. Use when the user says "plan this in Linear", "create Linear tickets", "break this down into tasks", "push to Linear", "set up our board for this feature", or wants to turn a description or spec into well-structured, agent-ready Linear issues. Requires the official Linear MCP server to be configured.

This skill provides guidance for building MCP Apps, the official MCP extension (io.modelcontextprotocol/ui) for rendering interactive HTML UIs inside MCP hosts. This skill should be used when the user asks to "create an MCP App", "add UI to MCP tool", "build interactive MCP", "MCP App server", "ui:// resource", "sandboxed iframe MCP", "interactive chat UI", "embed UI in chat", "MCP tool with interface", or needs to build interactive HTML applications that render inside Claude Desktop, ChatGPT, or VS Code Copilot.

Upgrade a Next.js project to the latest version (v16) with Turbopack, async Dynamic APIs, Biome, and React 19.2. This skill should be used when the user says 'upgrade Next.js', 'migrate to Next.js 16', 'update my Next.js app', 'run the Next.js codemod', 'my Next.js version is outdated', or when a migration plan is needed before making Next.js changes. Also invoke when the agent needs baseline build metrics for before/after comparison, or when checking whether a project needs async API migration, middleware-to-proxy migration, or Biome adoption.

This skill should be used when the user wants to query Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Provides browser automation, library management, and persistent auth. Drastically reduced hallucinations through document-only responses.

This skill should be used when the user wants to publish a package to npm, bump a version, release a new version, or mentions "npm publish", "bun publish", "version bump", or "release to npm". Handles version bumping, changelog updates, git push, npm publishing, and automatic token rotation via agent-browser when auth expires. Do not trigger for unrelated uses of "release" (e.g. GitHub releases, press releases).

Build, publish, and install Paperclip plugins correctly. This skill should be used when scaffolding a new Paperclip plugin, writing a plugin manifest, implementing plugin worker logic, adding UI slots, publishing to npm, or installing a plugin into a Paperclip instance. Contains critical lessons from real publishing failures. Also invoke when working on plugin capabilities, jobs, webhooks, agent tools, or the plugin SDK.

Run local performance audits on a project without network calls. This skill should be used when the user says 'audit performance', 'check bundle size', 'find large images', 'check for heavy dependencies', 'run a perf audit', 'how big is my bundle', 'optimize images', 'find oversized assets', or before any performance optimization work. Also use when an agent needs baseline metrics before making changes. All scripts output structured JSON to stdout.

Capture writing style profiles, track a pool of users, scan social intelligence, and apply style-matching to draft content. Use when asked to "capture my writing style", "draft a post in my voice", "scan what's trending", "add someone to the pool", or "track @username".

This skill should be used when the user wants to integrate Plaid API for bank account connections and transaction syncing. Use when implementing financial data access, bank linking, or transaction imports in TypeScript/Bun applications.

Finds stale and resource-hungry processes, scores them by waste, and presents a cleanup report with friendly names. Use this skill when the user says 'what's eating my RAM', 'kill stale processes', 'clean up my machine', 'free up memory', 'my computer is slow', 'what's running', 'too many things open', or asks to find/kill background processes. Also use proactively when you notice sluggishness, process spawn failures, or many duplicate processes during normal work.

Use this skill when preparing to publish a package, plugin, or skill and you need human approval first. Invoked when the user says "publish", "release", "ship", or "push to registry" but no approved Linear ticket exists yet. Runs preflight checks, creates or updates a Linear ticket with a structured release plan, moves it to Ready for Review, then stops — it does NOT execute the publish command.

Invoke this skill when: modifying any CLAUDE.md file, adding a new skill or agent to a plugin, user says 'update the skill map', 'add this to the map', 'register this agent', 'skills keep getting forgotten', 'I keep forgetting which skill to use', 'agents keep getting forgotten', 'add skill map', 'update agent map', 'sync skills to CLAUDE.md', or when setting up a new project. This skill injects compressed SKILL-MAP and AGENT-MAP directive blocks into CLAUDE.md so skill names and agent IDs persist across the session without fading from context. Skipping this means agents will forget skill names mid-session, fail to invoke the right skill, and guess at agent IDs — causing silent capability loss that is hard to diagnose.

Search and recall previous Claude Code conversation sessions. Use this skill whenever the user asks to remember, recall, find, or look up something from a past conversation or session. Triggers on phrases like: 'remember when we...', 'what did we do about...', 'find that conversation where...', 'when did I last work on...', 'what was that command/approach/solution we used for...', 'look up my past sessions about...'. Also use this skill when the user references prior work context that isn't in the current session, asks to continue work from a previous session, or wants to find a specific discussion, decision, or code snippet from their conversation history. Even vague references to past work ('that thing we did', 'the approach from last week') should trigger this skill.

Detects agent execution environment (Claude Code, Vercel Sandbox, or local dev) and adapts behavior accordingly. This skill should be used when an agent or bot needs to understand what runtime it is in, what tools are available, or how to adapt its behavior across different execution contexts. Use this skill when building agents that may run in Claude Code as subagents AND as hosted bots in Vercel Sandboxes, or when a SOUL.md/SKILL.md needs to work across runtimes.

This skill should be used when the user asks to "audit my SaaS", "check if I'm ready to launch", "review my launch checklist", "verify my pricing", "audit my payment setup", "check my AI visibility", "prepare for Product Hunt", "validate my SaaS for launch", or mentions launching a SaaS product. Provides a comprehensive, repeatable checklist with PASS/FAIL verification and actionable next steps.

This skill should be used when writing custom shaders for Three.js, creating visual effects with GLSL or TSL (Three Shader Language) for WebGL and WebGPU, debugging shader issues, building post-processing pipelines, implementing noise functions, procedural textures, or custom materials. Covers shader workflow, TSL node system, GLSL patterns, debugging, performance optimization, and post-processing with pmndrs/postprocessing.

This skill should be used when the user asks to "publish a plugin", "release a plugin", "bump plugin version", "update a Claude Code plugin", "publish skills", or mentions plugin publishing, plugin release, or skill distribution. Handles version bumping, changelog updates, git workflow, and publishing for both Claude Code plugins and standalone Agent Skills.

This skill should be used when the user asks to "create a status line", "customize status line", "set up statusline", "configure Claude Code status bar", "install ccstatusline", "add project colors to status line", "show git branch in status", "display token usage", or mentions Peacock colors, powerline, or status line configuration.

This skill should be used when building Three.js or React Three Fiber (R3F) projects, creating 3D scenes, animating meshes with useFrame, loading GLTF/GLB models, setting up physics with @react-three/rapier, using WebGPU with R3F, optimizing 3D performance, scaffolding Vite+R3F projects, or exporting R3F components. Covers scene setup, Drei helpers, asset pipeline, responsive canvas, and performance budgets.

Generate cohesive UI audio themes with subtle, minimal sound effects for applications. This skill should be used when users want to create a set of coordinated interface sounds for wallet apps, dashboards, or web applications - generating sounds mapped to UI interaction constants like button clicks, notifications, and navigation transitions using ElevenLabs API.

Clone real or fictional voices using ElevenLabs Instant Voice Cloning (IVC). This skill chains together the full pipeline — finding reference audio, preparing samples, uploading to ElevenLabs IVC, testing the clone with text-to-speech, and tuning voice settings. Use this skill whenever the user wants to clone a voice, create a custom voice from audio samples, replicate a famous voice style, or build a voice for a character. Covers celebrity impressions, fictional characters, branded voices, and personal voice clones.

Wait for CI/CD pipelines to complete after pushing code, then act on results. This skill should be used after git push, after creating a PR, when the user says 'wait for CI', 'check if the build passes', 'monitor the pipeline', 'wait for checks', 'is CI green?', or whenever the agent needs to verify that pushed code passes CI before proceeding. Also use when an agent workflow involves push-then-verify cycles, deployment monitoring, or needs to block on CI results before taking the next step. Supports GitHub Actions, GitLab CI, and Vercel deployments.

This skill should be used when dispatching more than 5 parallel agents, when context budget management is needed, or when generating multiple variations of the same output. Complements superpowers dispatching-parallel-agents with wave sizing, context budget tracking, and directive diversity. Use when the user says 'fan out', 'generate variations', 'batch agents', 'wave dispatch', or when spawning large numbers of subagents.

AI-powered X/Twitter research via xAI Grok. Returns AI SUMMARIES with analysis, not raw tweets. Use for "what's trending", "social sentiment", "summarize X discussion about", "analyze X conversation about", "research topic on X". For RAW tweet data, use x-user-timeline, x-tweet-search, x-tweet-fetch instead. Requires XAI_API_KEY.

Fetch a specific tweet by URL or ID. Use when user shares an X/Twitter URL (https://x.com/... or https://twitter.com/...), asks "get this tweet", "fetch tweet", "what does this tweet say", "read this X post". Requires X_BEARER_TOKEN.

Search recent X/Twitter posts by query. Returns RAW TWEETS (last 7 days). Use when user asks "search X for", "find tweets about", "what are people saying about", "Twitter search", "raw tweets about". For AI summaries/sentiment, use x-research instead. Requires X_BEARER_TOKEN.

Get X/Twitter user profile by username. Use when user asks "who is @username", "get X profile", "lookup Twitter user", "find X account", "user details", "follower count for". Requires X_BEARER_TOKEN.

Get recent tweets from an X/Twitter user. Use when user asks "what has @username posted", "recent tweets from", "user's X posts", "show timeline for", "what is @user saying". Requires X_BEARER_TOKEN.

7 hooks across 3 events