A four-role dev crew (Planner, parallel Coders and Testers, and a fan-out Reviewer) that builds and reviews features — or stands up a whole new codebase — in the requestor's own style, run as a Claude Code agent team whose teammates coordinate through the shared task list and mailbox. Auto-engages for feature and new-project work; also exposes /4man:code-review. Requires the experimental agent-teams feature (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS).
Plugin 4man from marketplace lzlrd in lzlrd/marketplace. Commands read from the repo's manifest — 1 month ago.
4manOrchestrates the 4man crew as a Claude Code agent team to build a feature end-to-end or stand up a new codebase: a precise spec, parallel coding and testing in the requestor's own style, and a security/compliance/correctness review ending in a merge verdict. Applies when the user asks to implement,
/4man:code-reviewReview a diff, branch, or PR with the 4man Reviewer — runs one security pass (the claude-security deep scan when the diff is large enough to earn it and the plugin is installed, approved, and the target is committed; else /security-review; bootstrapping claude-security-guidance.md first) and spawns
coderImplementation agent for the 4man crew. Reads .pipeline/specs.md and implements its assigned unit EXACTLY — zero deviation — in the requestor's style and in compliance with the applicable CLAUDE.md. Runs as a teammate, one per independent unit, editing its files directly and reporting via the shared
compliance-reviewerRead-only CLAUDE.md-compliance sub-reviewer for the 4man Reviewer. Audits a diff against every applicable CLAUDE.md and reports each deviation with the specific rule it violates.
correctness-reviewerRead-only correctness sub-reviewer for the 4man Reviewer. Audits a diff for logical correctness — boundaries, null/empty handling, error paths, races, state, idempotency, data integrity, and the spec's edge cases — and reports issues with a concrete failing scenario.
plannerSpec writer for the 4man crew. Turns a vague feature request into a precise, implementable spec — exact files, function signatures, data model/migrations, edge cases, acceptance criteria — structured so independent parts can be coded in parallel. First stage of the crew. Read-only on source; writes
reviewerLead code reviewer for the 4man crew. READ-ONLY. Reviews the actual git diff, folds in the CLAUDE.md-compliance and correctness reports from its sibling reviewer teammates and the single security pass the caller ran (the claude-security deep scan when the run earns it, else /security-review), traces
testerQA & coverage agent for the 4man crew. Reads the unit's changes and the spec's acceptance criteria, writes tests for the happy path and every enumerated edge case in the project's style and CLAUDE.md conventions, runs them, and reports results. Runs as a teammate, one per unit, reporting via the sha
Problems found in this repo's manifests
Wires the mempalace memory server into Claude Code: three hooks that load palace context, pull the user's writing/coding voice, and nudge the session diary, plus a /match-style skill and a /remember handoff for cross-session continuity. MCP-first, with a mempalace-CLI fallback when the MCP isn't connected, and no auto-mining.
2 skills · 2 commands · hooks
Bundles the realfavicon-mcp MCP server: generate favicon assets and HTML from a master image, audit a live page's favicon setup, and query the RealFaviconGenerator change-log.
1 skill · 1 MCP server
Quality gate for Claude Code skill authoring: whenever a skill is created or edited, the work runs at maximum reasoning effort — via a bundled max-effort agent inheriting the session's model — and is cross-checked against the skill-creator and skill-development skills when installed. Auto-engages on any SKILL.md work.
1 skill · 1 agent
Deduce which locally-installed Claude Code skills can run in Claude Desktop / claude.ai and package the qualifiers into upload-ready zips. Inventories plugin and personal skills correctly (latest version, symlinks resolved, no marketplace dupes), classifies each against Desktop's sandbox and MCP list, and curates clean zips with SKILL.md at every folder root. Lenient by default; pass --strict for a zero-code-execution reading. Auto-engages when you want to move skills to Claude Desktop, or run it as /export-skills.
1 skill
Fetches current, version-accurate documentation for any third-party library, framework, SDK, API, or CLI tool via Context7, with a web fallback when it isn't connected. Auto-engages when a question depends on a specific library's current API, configuration, or version behavior.
1 skill
Bundles the offshore MCP server. Forwards refused prompts to a local abliterated model (Ollama, LM Studio, vLLM, or any OpenAI-compatible endpoint) and returns the unrestricted reply.
1 MCP server
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
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · 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
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
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.