Plugin Claude Code
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Plugin Claude Code
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Plugin Claude Code
Bundles 6 skills · 320 tokens together
Measurement-first Agent Skills for Lighthouse, Chrome DevTools, Core Web Vitals, WCAG 2.2, SEO, and agentic browsing.
Skill Claude CodeCodex
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…
Command Claude Code
Co-write a piece with clarity, starting from an interview.
Command Claude Code
Review a draft with clarity, without rewriting it.
Command Claude Code
Rewrite a draft with clarity.
Skill Claude CodeCodex
Claim and implement one ready GitHub issue, run fail-closed gates, obtain independent verification, and open a draft pull request.
Skill Claude CodeCodex
Inspect factory health, stale work, CI, security advisories, and recent run evidence without implementing fixes.
Skill Claude CodeCodex
Turn an ambiguous factory issue into human-approved product, behavior, design, and implementation slices. Use interactively before implementation.
Skill Claude CodeCodex
Show the factory control room from live GitHub labels, open PRs, recent run records, gate health, and charter limits.
Skill Claude CodeCodex
Classify GitHub issues into the factory's live label queue and write an auditable snapshot. Use for backlog triage or a scheduled triage run.
Skill Claude CodeCodex
Review factory evidence and propose tighter or looser constraints without editing the charter. Use for a periodic constraint review.
Skill Claude CodeCodex
Independently verify a factory pull request, including fail-closed gates, negative test proof, scope, and load-bearing review.
Agent Claude Code
Adversarial reviewer for factory PRs and specs. Argues the case against a change - what breaks, what was assumed, what maintenance cost is being deferred. Use on load-bearing changes, before approving a spec, or when a change looks suspiciously clean.
Agent Claude Code needs its repo
Independent verification of a factory change. Reads the diff cold, re-runs gates itself, and reaches its own verdict without trusting the implementer's account. Use after factory-implement completes and before any PR is opened.
Command Claude Code
Review factory performance and propose deliberate constraint changes - tighten where a gate let something through, loosen where a class of change has been green long enough.
Command Claude Code
Factory control room. Show queue state, review bottleneck, and what needs a human right now.
Hook Claude Code
One of 2 in settings.json
Runs before the agent uses a tool for Bash tool calls, executing block-merge.sh via bash with --show-toplevel. From addyosmani/factory.
Settings file Claude Code
One of 2 in settings.json
Agent settings declaring 1 hook event (PreToolUse) and 6 allowed tools.
Skill Claude CodeCodex
Multi-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: