Development formatting hooks (Go, Shell, Proto, OpenAPI), TDD agents, grill-with-docs, pi-implementer (a local model implements Tickets through pi + pi-vcc under Claude Code's supervision), and second-opinion (Muse Code reviews Diffs and Plans read-only; Claude verifies and rebuts), consensus-review (security, cleanup and bug reviewers, then a blind Verifier per Finding; only medium+ Findings the Verifier confirms reach you), plus mods: Crawler Points HUD, Dispatch Board, Podman Guard, Branch Guard, TDD Band, Floor Boss, Sponsor Mail (PR watch), Beast Watch (GPU box health + Beast Guard) and the System's voice (its Cues are heard by dungeon-buddy)
Plugin dotfiles-dev-tools from marketplace anthony-bible-dotfiles in Anthony-Bible/dotfiles. Commands read from the repo's manifest — 9 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
consensus-reviewVerified multi-agent code review. Three read-only reviewer subagents (Security, Optimizer/Cleaner, Bug Hunter) review the same frozen Diff once; every distinct medium+ Finding then goes to its own blind, adversarial Verifier, and the user sees only Findings the reviewer and the Verifier independentl
grill-with-docsGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
pi-implementerHybrid implementation — this Claude Code session scopes and writes one-file Tickets (Orchestrator), a local model on llama-server implements each one through pi + pi-vcc in a fresh session (Implementer), and this session gates every result with the toolchain, a diff review and one commit per accepte
second-opinionSecond set of eyes from a different model family. Meta's Muse Code (the Reviewer) reviews a Diff or a Plan in a read-only snapshot, and this session (the Author) verifies every Finding and argues back once before the user sees anything. Use BEFORE every git commit or PR (`git commit`, `gh pr create`
ticket-creationUsed for creating an issue. This will make sure it has enough technical detail and business requirmenets. Use this whenever the user asks to create a ticket or issue for a project. This will make sure the issue is well defined and can be easily understood by the development team.
green-phase-implementerUse this agent when you have failing tests and need to write the minimal code necessary to make them pass. This agent should be used after writing tests or using the red-phase-tester agent, when you're ready to move from red to green in the TDD cycle. Examples: <example>Context: User has written tes
pem-pm-scoperUse this agent when a user needs help scoping out the business context of a ticket, issue, or feature request — including writing user stories, defining the 'why', identifying stakeholders, clarifying acceptance criteria, and ensuring the business value is clearly articulated before development begi
red-phase-testerUse this agent when you need to generate failing tests for the red phase of TDD before implementing any new functionality. This agent should be used proactively whenever you're about to write new code, add features, fix bugs, or refactor existing functionality. Examples: <example>Context: User is ab
security-auditorSpecialized in finding security vulnerabilities in code.
tdd-refactor-specialistUse this agent when you have just completed the green phase of TDD (making tests pass) and need to refactor the implementation code. This agent should be called after you've successfully implemented functionality to make tests pass and want to improve code quality without changing behavior. Examples
tdd-review-agentUse this agent proactively after the refactor phase of TDD cycles to verify implementation completeness and quality. Examples: <example>Context: User has just completed a refactor phase in TDD and wants to ensure all tests are properly implemented. user: 'I just finished refactoring the user authent
tech-requirements-gathererUse this agent when you need to gather, refine, or enhance technical requirements for a feature, bug fix, or agent configuration. This agent is ideal for turning vague descriptions into actionable Github/Gitlab issues with specific technical details, identifying edge cases, caveats, and implementati
sequential-thinkingruns: npx -y @modelcontextprotocol/server-sequential-thinking
${CLAUDE_PLUGIN_ROOT}/scripts/openapi-lint.sh
${CLAUDE_PLUGIN_ROOT}/scripts/shellformat.sh
${CLAUDE_PLUGIN_ROOT}/scripts/goformat.sh
${CLAUDE_PLUGIN_ROOT}/scripts/protoformat.sh
goBuddy: /buddy hatches your dungeon pet from your account. It sits above the prompt, fidgets, and talks about your session's Mishaps and Long Hauls, or, with dotfiles-dev-tools installed, back to the System's Cues (a Reroll then costs Crawler Points)
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
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.