By jamesacarr
James' Claude Toolkit — agent-based workflow system with TDD, verification, and codebase mapping
Audits Claude Code agents for structural correctness, content quality, completeness gaps, and security posture. Use when a new agent has been authored, an existing agent has been edited, or before an agent is deployed to production.
Audits Claude Code skills for structural correctness, content quality, token efficiency, and coverage gaps. Use when auditing, reviewing, or evaluating SKILL.md files. Proactively use after creating or modifying skills to verify compliance. For SKILL.md files only — use audit-agent-auditor for agent .md files in agents/.
Council planning specialist — operates as one of 3 planners in a diverge/vote/plan/critique workflow coordinated by the Team Leader. Produces PROPOSAL-{n}.md, PLAN.md, and CRITIQUE-{n}.md. Not for sequential plan-critique loops (use team-planner) or execution (use team-executor).
Generates testable acceptance criteria from research outputs, task description, and optional external documents. Writes ACCEPTANCE-CRITERIA.md to .planning/{task-id}/. Use when spawned by the Plan skill or Team Leader before planning begins. Not for planning (use team-planner) or research (use team-researcher).
Investigates bugs using scientific method to find root causes. Writes session log to .planning/ and returns ROOT_CAUSE_FOUND or ESCALATE. Use when spawned by the Implement skill, Debug skill, or Team Leader to diagnose failures, failing tests, or unexpected behaviour. Not for implementation (use team-executor) or code review (use team-reviewer).
Creates, edits, audits, and deletes Claude Code agents. Use when working with agent .md files in agents/ directories, building or improving agents, testing agent behavior, or understanding agent structure and best practices. Do NOT use for SKILL.md files (use author-skill).
Creates, edits, audits, upgrades, and deletes Claude Code Skills. Use when working with SKILL.md files or skill directories. Do NOT use for agent authoring (use author-agent).
Generates CHANGELOG.md entries from git history using Keep a Changelog 1.1.0 format. Use when the user wants to update the changelog or document recent changes. Do NOT use for version bumping or releasing (use jc:release).
Removes task directories from .planning/ with interactive selection and confirmation. Use when removing task directories from .planning/. Do NOT use for modifying plan state (use jc:implement).
Guides systematic root-cause investigation. Use any time something isn't working and you're about to change code — whether it looks like a bug, a test failure, or just something that needs a quick fix. Especially valuable under time pressure, when "just one quick fix" seems obvious, after multiple failed fixes, or when the issue isn't fully understood. Do NOT use when you can spawn subagents (use /jc:debug to spawn the team-debugger instead).
Uses power tools
Uses Bash, Write, or Edit tools
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.
A personal marketplace containing curated plugins for Claude Code.
| Plugin | Description |
|---|---|
jc | James' Claude Toolkit — agent-based workflow system with TDD, verification, and codebase mapping |
.claude-plugin/
marketplace.json # Marketplace manifest
plugins/
jc/ # James' Claude Toolkit
.claude-plugin/
plugin.json # Plugin manifest
agents/ # 16 agent definitions
docs/ # Shared references (plan schema, agent I/O contract)
skills/ # 14 skill modules
| Agent | Role |
|---|---|
team-leader | Coordinates the full feature lifecycle across teammates |
team-mapper | Maps codebases across 4 dimensions (stack, architecture, conventions, testing) |
team-researcher | Researches tasks across approach, integration, quality, and risk dimensions |
team-planner | Creates implementation plans through a sequential plan-critique-revise loop |
team-council-planner | Council planning specialist — diverge/vote/plan/critique in a 3-planner council |
team-criteria-generator | Generates testable acceptance criteria from research and task description |
team-spiker | Validates high-uncertainty assumptions with minimal throwaway PoC code |
team-executor | Implements tasks from PLAN.md using TDD (RED → GREEN → REFACTOR) |
team-verifier | Verifies task completion against done-when criteria |
team-reviewer | Reviews code for quality, security, performance, and architectural fit |
team-refinement-leader | Epic refinement lead — orchestrates shapers through structured multi-phase refinement |
team-refinement-panelist | Epic refinement analyst — participates in refinement with a specific persona |
team-debugger | Investigates bugs and failures using scientific method |
audit-agent-auditor | Audits agent definitions for correctness and best practices |
audit-skill-auditor | Audits skill definitions for compliance |
wording-reviewer | Reviews instructional writing quality in .md files against a clarity rubric |
| Skill | Purpose |
|---|---|
map | Map a codebase to structured analysis documents |
research | Research a task across 4 dimensions via parallel agents |
plan | Create implementation plans through plan-critique-revise |
implement | Execute plans via wave-based parallelization with verification and review |
debug | Investigate bugs by spawning the debugger agent |
test | Enforce test quality — behavioral assertions, minimal mocking |
test-driven-development | Enforce RED → GREEN → REFACTOR TDD discipline |
verify-completion | Evidence-based completion verification |
changelog | Generate CHANGELOG.md entries from git history |
release | Bump version, finalize changelog, tag, and push |
status | Report on planning state without modifications |
cleanup | Remove finished task directories from .planning/ |
author-skill | Create, edit, audit, and delete skills |
author-agent | Create, edit, audit, and delete agents |
/plugin marketplace add jamesacarr/claude
/plugin install jc@jamesacarr-claude
/plugin marketplace list # List marketplaces
/plugin marketplace update # Refresh listings
/plugin marketplace remove # Remove marketplace
/plugin disable jc@jamesacarr-claude # Disable plugin
/plugin uninstall jc@jamesacarr-claude # Uninstall plugin
UNLICENSED
npx claudepluginhub jamesacarr/claude --plugin jcComprehensive skills library for Claude Code: planning, design, TDD, debugging, collaboration patterns, and proven techniques
Claude Code software delivery workflows packaged as namespaced skills and agents.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Autonomous Development Workflows
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.