claude-md plugins

by Alireza Rezvani

CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.

by Vinta Chen

Opinionated agentic skills that do the boring parts for you

by Alberto Leal

Install and maintain a "model routing" section in a project's CLAUDE.md that teaches Claude Code which model to use for which work, including delegating to GPT models via the Codex CLI. Use when adding model-picking guidance to CLAUDE.md, setting up Codex/GPT as a delegation target or fallback, or routing subagent and workflow tasks across models by cost, intelligence, and taste.

by Melodic Software

Keeps a repo's Claude Code memory layer healthy and under your control, against criteria derived from official Claude Code documentation. The audit skill checks the instruction/memory layer (CLAUDE.md, a root AGENTS.md, CLAUDE.local.md, .claude/rules/, auto-memory) with a deterministic script-backed spine plus judgment-tier checks. The stateless skill inspects, disables, and (confirm-gated) purges Claude-written auto memory across all settings scopes.

by Jordan Richlen

Audits CLAUDE.md/AGENTS.md/SKILL.md instruction files against current repo state, catches claims that have gone stale (a renamed path, a dropped command, a policy that changed) before they get trusted or acted on, and resolves contradictions between layered instruction files (root vs nested, SKILL.md vs its parent AGENTS.md) down to one explicit kept version instead of leaving both to stand. Use before trusting or propagating any instruction-file claim you haven't personally re-checked, whenever onboarding a repo's docs for the first time, right after a refactor/rename/policy change that could invalidate what's documented, or whenever two instruction files (or an instruction file and the actual repo) say different things about the same fact. Trigger phrases: 'audit the docs', 'is AGENTS.md still accurate', 'clean up CLAUDE.md', 'these instructions contradict each other', 'refactor the AGENTS.md files'.

by Dylan Claywell

Write or revise a project's CLAUDE.md: the working agreement, the levers that differ per team, and the template.

by Marco Markl

Persönliches Planungs-Toolkit: Vorhaben klären (plan-grill), Plan reviewen (plan-review), umsetzen (plan-execute), durch die Projekt-Einrichtung lotsen (project-setup), Projekt-Settings einrichten (project-settings), Projektablage strukturieren (project-structure), den projekteigenen Prompttext prüfen (project-audit), CLAUDE.md härten (project-rules), sie kuratieren (project-curate), aus der Session lernen (session-learn), den Arbeitsstand übergeben (session-handoff) und ihn im neuen Fenster wieder aufnehmen (session-resume).

by ContextOps

Team context sync for Claude Code — 승인된 팀 컨텍스트를 모든 팀원의 Claude Code 에 같은 버전으로 배포한다

by Sid

How to write instruction files for AI agents

by Calvin Dittkrist

The repository standard: AGENTS.md with a CLAUDE.md import, the make check gate, architecture.md, ADRs, PR template, workflow settings, and a check that fails on stray agent configuration. Skills: /standardize (six read-only auditors, one findings report), /apply (backup, cleanup pull request, issues, GitHub workspace), /adr, /docs-check.

by Rahmat Eka

Bootstraps a structured AI-agent instruction system for a sibling-folder multirepo workspace — parent AGENTS.md, per-repo AGENTS.md, and a canonical docs repo with PRD/TRD/ERD/Design-System/API-Contracts, agent role files, playbooks, exec-plans, and a quality score.