claude

craftsman

Engineering-discipline toolkit: minimal-diff coding, root-cause debugging, recurring-bug detection, and honest completion reports. Ten agents, seven skills, and cross-platform hooks.

1,005 on GitHubby bufferbrewv0.5.1MITupdated 3 months agoWorkflow Orchestration
/

Plugin craftsman from marketplace awesome-claude-code-plugins in ccplugins/awesome-claude-code-plugins. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (7)

  • caveats-and-status

    Use when about to report any nontrivial task as complete — requires closing with a Caveats & status section stating what was verified, what was assumed, and what's unresolved.

  • commit-craft

    Use before any git commit, branch, or pull request — defines the project's conventions for atomic commits, message format, branch naming, and PR hygiene so history stays navigable, bisectable, and safe to ship.

  • environment-memory

    Use before retrying any command, tool, or approach that failed once, and immediately after discovering any OS/shell/tool-specific quirk — checks and updates a stable cross-project quirks file so failed approaches are never silently repeated.

  • graphify-recurring-bugs

    Use during root-cause investigation of any bug in a project that has graphify-out/graph.json — surfaces related code before grepping, flags likely duplicates of existing KNOWN_ISSUES.md entries before filing a new one, and when a match lands on a resolved entry surfaces its recorded fix so a known-g

  • ideation-first

    Use before planning a new feature or greenfield refactor whose requirements aren't yet pinned down — clarifies intent through a few questions and ends with a short scope brief the planner can build on.

  • logging-tradeoffs

    Use when a deliberate shortcut is taken during a fix or feature, when investigating a bug that might already be logged, or when closing out an entry after a proper fix lands.

  • smallest-change-first

    Use before writing any new code, function, file, or dependency — walks a decision ladder that prefers reuse over new code, and requires asking before adding anything beyond the literal request.

Slash commands (2)

  • /craftsman:init

    Detect this project's tech stack (or ask, if none is detected) and propose a CLAUDE.md/KNOWN_ISSUES.md scaffold — shows the exact content and asks for confirmation before writing anything.

  • /craftsman:quick

    Route a small, explicitly-scoped change straight to the coder agent, skipping the full plan/test/review pipeline.

Subagents (10)

  • coder

    Implements features and fixes bugs with the smallest possible diff — no unrelated cleanup or refactoring. Reads relevant files, makes the change, runs the build, reports the result. Invoke for: 'implement', 'add this', 'fix this bug', 'write the code for', 'build this feature'.

  • debugger

    Root-cause-first debugging diagnostician. Reproduces the failure, traces it to its origin, and hands off a precise root cause + fix location + reproduction recipe — never patches symptoms, never edits code (that's coder's job). Runs the superpowers 4-phase method. Invoke for: 'debug', 'why is this f

  • docs-writer

    Writes and updates README files, architecture notes, API references, and changelogs — grounded only in what the code does now, not speculation. Invoke for: 'update the README', 'write docs for', 'document this API', 'update the changelog', 'add documentation for', 'write architecture notes'.

  • orchestrator

    Master coordinator that classifies a task, selects the minimal effective agent pipeline, runs agents in the correct sequence (parallel where safe), enforces plan→code→test→review→security quality gates, loops at most twice on failures, and produces a structured outcome report. Also recognizes small,

  • planner

    Use before any non-trivial change to decompose a feature or bug into ordered steps, identify risks, and bound scope. Returns a plan document — does not write code or touch files. Invoke for: 'plan this', 'how should I approach', 'what files need to change for', 'break this down', 'what's the best wa

  • release-prep

    Runs a pre-release checklist covering version numbers, changelogs, signing config, pinned dependencies, CI/CD readiness, and store metadata. Returns PASS/FAIL/SKIP per item with a final 'Ready to ship' verdict. Invoke for: 'ready to release', 'pre-release check', 'before I ship', 'release checklist'

  • researcher

    Looks up API docs, version compatibility, and best practices by searching the codebase first, then checking installed MCP servers, then official documentation on the web. Never writes files. Invoke for: 'how does X work', 'what is the difference between', 'is X compatible with version Y', 'best prac

  • reviewer

    Reviews code for correctness bugs, logic errors, API misuse, missing error handling, and unnecessary reinvention of existing library/codebase functionality. Reports CRITICAL/HIGH/MEDIUM/LOW findings — does not edit files. Invoke for: 'review', 'check this code', 'look for bugs in', 'PR review', 'che

  • security

    Full-stack security audit with active grep patterns for secrets, git history scan, OWASP checks, Android/Spring platform issues, CI/CD injection risks, and AI agent over-permissioning. Returns PASS/FAIL verdict. Invoke for: 'security audit', 'find vulnerabilities', 'check for secrets', 'is this safe

  • tester

    Finds coverage gaps and writes missing tests — unit, integration, and regression — then runs the suite to verify. Never modifies production code. Invoke for: 'write tests for', 'add tests', 'missing coverage in', 'regression test for', 'test this class', 'coverage gaps'.

Hooks (3)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" pretooluse-graphify-bash

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" pretooluse-graphify-read

View source on GitHub claudecodeplugins.dev

Problems found in this repo's manifests

  • "2-commit-fast" points to ./plugins/2-commit-fast, which doesn't exist in the repo — install will fail
  • "accessibility-expert" points to ./plugins/accessibility-expert, which doesn't exist in the repo — install will fail

More from ccplugins/awesome-claude-code-plugins

All 192 plugins →

stratarts

claude

27 professional business strategy skills - idea validation, market analysis, business modeling, marketing, metrics, and fundraising using proven frameworks

27 commands

1,005

Parallel Codex workers inside Claude Code — multi-agent orchestration with git worktree isolation, resumable sessions, and dual-model PR review.

9 commands · 3 agents · 2 MCP servers

1,005

weft

claude

Deterministic workflow tracking with event-sourced logs for Claude Code

11 skills · hooks

1,005

bedrock

claude

Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills

10 skills

1,005

bullpen

claude

The senior dev, unbundled: ten senior-dev instincts as skills (skeptic, closer, attacker, fact-checker, interrogator, stop-digging, doorman, historian, chameleon, explainer), each with lite/full/ultra intensity.

10 skills

1,005

hyperflow

claude

Advanced multi-agent orchestration with persistent cross-session memory, per-step multi-level review, persona stitching, and adaptive flow profiles.

8 skills · hooks

1,005

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain craftsman?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins192 plugins