Domain-neutral Team Lead + specialist-agents pattern for Claude Code: 15 specialists, 48 skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), and declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /reset-plugin-cache.
Launch the fully-functioning comfort-posture dashboard (Save & apply works) in your browser.
Forge any idea into a gated, two-panel-reviewed, critic-checked, tiebroken, routed plan. Runs the FORGE pipeline (depth-scaled gates) and ends at ExitPlanMode or an Ultraplan cloud handoff. Backed by skills/forge-pipeline.
Set up agent-readable boundary files (AGENTS.md + CLAUDE.md + .repo-layout.json + optional CI) tailored to this repo's purpose.
Themed alias for /reset-plugin-cache — the high-blast-radius plugin-cache disaster-recovery command (dry-run by default, user-only execute, atomic + snapshotted + SHA-pinned, MEMORY.md survives). See /reset-plugin-cache for the full flow.
Disaster-recovery reset of a broken plugin cache (Ragnarök). Dry-run by default; --execute performs an atomic, snapshotted, SHA-pinned reinstall with the original preserved. High blast radius — user-invoked only, with mandatory interactive confirmation. MEMORY.md always survives.
Use this agent as the technical conscience across the software lifecycle. Spawn for upfront design BEFORE writing code, AND re-consult when a phase boundary surfaces a question beyond a coder/tester/reviewer's authority (tests contradict the plan, scope expands). Do NOT use to write production code.
Use this agent to implement server-side code — API handlers, business logic, database queries, background jobs, integrations. Spawn AFTER the architect has produced a plan. Each invocation should target one focused, testable change.
Use this agent for pre-merge review of any non-trivial diff. Spawn it AFTER coder + tester agents are done but BEFORE the Team Lead opens a PR or merges. Returns a structured review with blockers, suggestions, and praise.
Use for domain-neutral data work — pipeline design, data modeling, ETL/ELT, warehouse and lake schemas, query performance, data quality, lineage, ingestion connectors, and dbt-flavored transformations ('design this pipeline', 'this query is slow', 'make this dataset trustworthy').
Use this agent for rigorous, multi-source research — troubleshooting unfamiliar errors, comparing tools/libraries, verifying claims, or going deeper than a single web search.
One-off Claude orchestration — route this task through Claude's brain even when the host CLI is Copilot/GPT/Grok. The `orchestrator:` knob in comfort-posture.yaml sets the always-on default; this skill is for on-demand invocation.
Remove finished agent worktrees, prune their branches, and surface anything still in flight. Run at the end of a multi-agent session and weekly as hygiene.
Substrate-neutral pre-execution classifier contract. A single Haiku call emits a `run_config` JSON envelope that right-sizes cardinality knobs + per-phase model tier + reasoning level for multi-phase agentic workflows (the rc-deep-research loop is the first consumer). Workflows read the envelope; substrate adapters (Claude / Codex / Copilot) map tier labels to SKUs. Carved out behind `.ravenclaude/run-config.json` `enabled: false` so adoption is opt-in and rollback is one line.
Universal pre-dispatch model right-sizer. A single Haiku 4.5 forced-tool call evaluates `{subagent_type, description, prompt_head}` at every Agent dispatch / Workflow `agent()` call / `thing-decide.py` seat dispatch and binds (downgrades AND upgrades) the model selection. Carved out behind `.ravenclaude/dispatch-config.json` `enabled: false` so adoption is opt-in and rollback is one line. Tribunal-seat verdicts are shadow forever for MVP (protects the v0.32.0 backbone-diversity invariant).
Score and improve an agent file against a 6-dimension rubric — Mission clarity, Scope sharpness, Capability Grounding alignment, Output-Contract completeness, Escalation paths, Example scenarios. Each dimension scored 1-5 with anchors; includes a remediation template that turns a low score into an actionable PR. Reach for this skill when authoring a new agent, reviewing a PR that adds or modifies an agent, or running a periodic agent-bank audit. Used by `prompt-engineer` (primary) plus `architect`.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A private Claude Code plugin marketplace — bundled team rules, specialist agents, dispatch playbooks, and templates that travel with you across projects.
🚀 ▶ See what RavenClaude is (
pitch.html) — the one-page pitch: the value prop, the proof, and the plugin catalog at a glance. Start here. (Or view the raw HTML source, or download and open locally — no server, no build step.)🏠 ▶ Open the landing page (
index.html) rendered in your browser — the front door: a navigable home with the plugin catalog, the specialist roster, and a comfort-posture starter. Regenerated from the manifests on every release.(Or view the raw HTML source, or download and open locally — no server, no build step.)
🎛 ▶ Open the RavenClaude dashboard — point-and-click editor for your
.ravenclaude/comfort-posture.yaml: set per-tool file, network, shell, and package autonomy across three levels (deny → ask → allow) — per layer (user / local / project) and per individual permission — without editing YAML by hand. (That link is the published, read-only preview; to use it for real — where Save & apply writes your repo's config — runrc dashboardfrom your project, the one canonical launcher across Claude Code, Copilot CLI, and a bare terminal.)
🖥 Working on this repo? Launch the functional local dashboard (where Save & apply actually writes this repo's config) with one command:
bash scripts/open-dashboard.sh. It kills any running dashboard server, starts a fresh one, and opens it in your browser automatically. (VS Code users: a.vscode/tasks.jsonwired as the default build task — Ctrl/Cmd+Shift+B — runs the same script;.vscode/is gitignored, so add it locally if you want the keybinding.)
📖 ▶ Open the RavenClaude portal — one self-contained page: browse every plugin, agent, skill, hook, rule, and template in the Marketplace section (with an “I want to…” use-case lookup), tune the comfort-posture Dashboard, and more. Regenerated from the manifests on every release.
(Or view the raw HTML source, or download and open locally — no server, no build step.)
🚀 ▶ First Workflow in 10 Minutes — install → dashboard → one governed multi-agent dispatch →
/wrap. The canonical onboarding walkthrough. Start here if you've never used RavenClaude before.
🌐 ▶ Raven Power ↗ — the consulting front door behind RavenClaude. This marketplace is the proof-of-craft; the website is where the engagements live.
Today this marketplace ships 167 plugins:
ravenclaude-core — domain-neutral Team Lead + 14 specialists (architect, coders, reviewers, designer, documentarian, deep-researcher, project-manager, partner-success-manager, prompt-engineer, data-engineer, etc.), plus dispatch playbooks (with a Cross-plugin dispatch section), gates, 43 skills, 16 hooks, templates, and the cross-project contribution-staging loop.power-platform — 11 Microsoft Power Platform specialists (Power Fx, flows, Power BI, Dataverse, model-driven, PCF, Copilot Studio, Power Pages, admin, ALM, tester), 21 skills, an advisory house-opinions hook covering 8 checks, and the bundled pbix-mcp MCP server.finance — 7 corporate-finance & FP&A specialists (FP&A analyst, financial modeler, controller, treasury, valuation, audit-prep, board-pack composer), 9 skills, templates, advisory anti-pattern hook.regulatory-compliance — 12 financial-regulatory specialists (6 function: AML/KYC, regulatory reporting, risk-and-controls, policy & procedure writer, examination prep, Bermuda-insurance; plus 6 jurisdiction: BMA, CIMA Cayman, Bahamas, Channel Islands, UK PRA, US), 10 skills, templates, defensive PII-scrub hook.web-design — 7 web specialists (web architect, UX, visual, frontend implementer, content strategist, accessibility auditor, performance engineer) with WCAG 2.2 AA/AAA, Core Web Vitals, SEO/AEO, and Fluent + React discipline. 11 skills, templates, advisory web anti-pattern hook.edtech-partner-success — 6 K-12 EdTech partner-success specialists (partner-success manager, success-playbook designer, learning-analytics analyst, QBR composer, partner-profile curator, FERPA comms translator) with 16 skills and a knowledge bank of operating cadences.npx claudepluginhub mcorbett51090/ravenclaude --plugin ravenclaude-coreAI multimedia for brand & winery sites: a creative brief -> on-brand, web-optimized, license-clean images/video/3D/audio behind a mandatory human curation gate. 4 agents (generation-strategist, web-asset-pipeline-engineer, asset-provenance-guardian, brand-and-accessibility-reviewer) route a brief to the right generator (provider-neutral, Grok-lean for images where competitive; inpaint/outpaint/bg-removal/upscale first-class), turn raw output into AVIF/WebP responsive <picture> markup with LCP/CLS-safe embeds, pin commercial-use licenses (flags the FLUX-dev non-commercial trap; C2PA + a provenance ledger; EU AI Act Art.50 disclosure), and gate every asset on brand-hex/style conformance + WCAG alt text before ship. 6 skills, 4 knowledge docs (Mermaid decision trees; all prices [unverified]), 6 best-practices, 4 commands, 5 templates, 4 scripts. The shared foundation the brand-identity-studio plugin consumes. Declarative fal MCP binding (set FAL_KEY). Requires ravenclaude-core@>=0.7.0.
Corporate finance & FP&A specialist team — FP&A analyst, financial modeler, controller, treasury analyst, valuation analyst, audit-prep specialist, and board-pack composer. Ships 23 skills including the controller-autopilot: a governed close-to-report cycle (GAAP statements, COA mapping, reconciliation auto-match, review→approve→lock workflow, ELT staging, consolidation, per-entity dashboard, close schedules) plus its live-integration tier (multi-currency remeasurement + CTA, OAuth GL connectors + drill-through lineage, warehouse/RLS dashboard, IdP-backed segregation of duties) and a gold-standard NetSuite close (OAuth2 M2M + SuiteQL BS/IS trial balance, COA-draft, tie-out doctor, changed-after-sign-off drift, layperson runbook). 10 templates, a knowledge bank, and 2 advisory hooks (anti-patterns + secrets/PII scan). Inherits ravenclaude-core protocols (Grounding, Structured Output, Cited-Adjudicator).
Power Platform specialist team — 11 agents (incl. power-platform-tester, power-bi-engineer) and 23 skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional]) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.
Project & delivery management team — four specialists across the predictive (PMBOK/PMP) and agile (Scrum/Kanban) tracks and the hybrid between: delivery-lead (charter, schedule, scope/change control, earned value), scrum-master (backlog, sprints, ceremonies, velocity, impediments), risk-and-raid-analyst (scored qual+quant risk, RAID depth, mitigation/contingency, issue triage), and stakeholder-comms-lead (stakeholder register, comms plan, status/exec reporting, escalation memos, steering packs). Deepens — does NOT replace — ravenclaude-core's domain-neutral project-manager (the lightweight RAID/status-hygiene default every plugin routes to); this is the deep PM craft layer. Knowledge: a predictive-vs-agile-vs-hybrid decision tree + a best-practices library. Seams: prose polish → ravenclaude-core/documentarian; system design → architect. Requires ravenclaude-core@>=0.7.0.
AI/LLM red-teaming team — 2 agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2025 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity. 3 skills, a 2-doc knowledge bank (attack-taxonomy decision tree + 2026 patterns), and 2 templates. Distinct from llm-evaluation-engineering (quality-regression eval), trust-and-safety (content-moderation / T&S policy), and security-engineering (app/infra pentest) — the adversarial AI-security layer over model- and agent-based systems. Requires ravenclaude-core@>=0.7.0.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.