By vmaia00
Vendored full copy of ECC (affaan-m/ECC) v2.0.0: 64 agents, 262 skills, 84 commands. MIT-licensed — see LICENSE and ATTRIBUTION.md. Most components are language/framework-specific; install only if you want the whole catalog.
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
Pull the latest ECC repo changes and reinstall the current managed targets.
Detect the project build system and incrementally fix build/type errors with minimal safe changes.
Create, verify, or list workflow checkpoints after running verification checks.
Code review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode)
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
Analyze code comments for accuracy, completeness, maintainability, and comment rot risk.
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.
Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
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.
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
A central, maintained-in-one-place set of Claude Code foundations that other repos pull from, while each repo keeps its own domain-specific agents/rules locally.
It's a Claude Code plugin marketplace. The shared layer ships as the core plugin; your
repo's own .claude/ is the local layer and overrides anything in the plugin with the same
name. Update centrally here, then git pull lands in every consuming repo with one command.
core providesexplorer, planner, builder, reviewer) — the orchestrator subagent set.new-project) — generic sub-project scaffolder.init-repo) — seeds a minimal starter CLAUDE.md (+ AGENTS.md pointer) for a new repo's local layer.secret-scan) — blocks Write/Edit/MultiEdit that contain real-looking credentials.session-start) — injects a concise standing directive (orchestrate · prefer existing skills/agents · define-done-then-verify · gate changes · untrusted-content baseline) at every session start.diagnose, write-a-skill, handoff, zoom-out, caveman) — curated engineering/productivity skills vendored from mattpocock/skills (MIT; see plugins/core/docs/THIRD-PARTY-NOTICES.md)./plugin marketplace add vmaia00/claude-specs
/plugin install core@claude-specs
/plugin marketplace update claude-specs
This git pulls the local clone and re-syncs the plugin. Bumping version in
plugins/core/.claude-plugin/plugin.json is what signals consumers there's a new version.
Point Claude Code at this folder directly instead of GitHub:
/plugin marketplace add ./claude-specs
/plugin install core@claude-specs
/reload-plugins # after editing plugin files
| Layer | Lives in | Example |
|---|---|---|
| Shared (pulled) | this repo's core plugin | generic builder, secret-scan, principles |
| Local (per repo) | each repo's .claude/ | domain agents/hooks that override the shared ones |
See BOOTSTRAP.md to stand up a brand-new repo on these foundations.
Heavier, dependency-bearing tools that are better consumed as their own installs than vendored into
core:
npx claude-mem install.See research/insights.md for a backlog of further patterns under evaluation.
Auto-update (track latest) and pinning (lock a version) are opposites — set up both so you can choose per machine/repo.
Cutting a release (do this on every change):
version in plugins/core/.claude-plugin/plugin.json. This is mandatory — if the
version string doesn't change, Claude Code keeps the cached copy and consumers never see your
update.main.plugin.json agrees with the marketplace entry):
claude plugin tag ./plugins/core --push -m "core %s"
Creates and pushes core--v<version> (e.g. core--v0.1.1).Track latest (default, recommended for your own machines): auto-update is enabled per
marketplace via "autoUpdate": true on the claude-specs entry under extraKnownMarketplaces
in ~/.claude/settings.json (or toggle it in /plugin → Marketplaces). The marketplace re-pulls
main at startup; you always get the newest version.
Pin a specific repo to a version (when you want stability): add a ref (tag/branch) or sha
to the plugin's source in marketplace.json. sha wins if both are set and survives branch
deletion:
{ "name": "core", "source": { "source": "github", "repo": "vmaia00/claude-specs",
"ref": "core--v0.1.1" } }
A repo using a pinned source ignores newer releases until you move the pin.
npx claudepluginhub vmaia00/claude-specs --plugin eccOrchestrator foundations: generic builder/explorer/planner/reviewer agents, a new-project command, a secret-scan hook, and universal working principles. Repo-specific agents/rules live in the consuming repo's .claude/ and override these.
Always-on multi-persona code-review pipeline: parallel distinct-angle reviewer panels → a Code Review Master that synthesizes one Solution → a second adversarial panel → Master 2 → an opt-in Executor & Fixer. No token optimization — every panelist is always spun up. Opt-in; install for deep, multi-perspective review.
Curated Ruby / Rails / Hotwire / TDD agent skills (28) + a code-reviewer agent, vendored (MIT) from superpowers-ruby, rails-agent-skills and ruby-core-skills. Opt-in; install for Ruby on Rails work. See ATTRIBUTION.md.
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
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
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.