claude-md repositories
Trending repositories tagged claude-md, ranked by trending score. Updated daily.
-
1
Sahir619/fable-method
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
GitHub · Python · 2,325 stars · 325 forks · +28 stars in 24 hours · Trending score 2.19
-
2
AIPMAndy/AndySoul
CLAUDE.md / AGENTS.md 规则模板:放进项目根目录,让 Claude Code、Codex、Cursor 少返工(附前后对比)|Drop-in rules for AI coding agents
GitHub · 115 stars · 19 forks · +3 stars in 24 hours · Trending score 0.94
-
3
nadimtuhin/claude-token-optimizer
Cut the tokens Claude Code loads at session start. CLI that sets up a small CLAUDE.md with on-demand docs, measures startup tokens, and keeps them small.
GitHub · JavaScript · 657 stars · 89 forks · 0 stars in 24 hours · Trending score 0.83
-
4
globalmpc/nomore
Finds the corrections you keep repeating to Claude Code and turns them into evidence-backed CLAUDE.md rules. Local CLI, no LLM by default, plus a public rule pack mined from claude-code issues
GitHub · TypeScript · 111 stars · 1 forks · +1 stars in 24 hours · Trending score 0.81
-
5
clirimajeti/codemyrules
Agent skill that turns a project's decisions, patterns and agent-doc instructions into lint rules, slims agent docs, and adds a silent lint feedback loop for agents.
GitHub · JavaScript · 19 stars · 1 forks · +1 stars in 24 hours · Trending score 0.73
-
6
Avinash-jetwani/jevmem
Shared project rules and memory for AI coding agents. Decisions, rules and failed approaches in one JEVMEM.md in your repo, read by Claude Code, Cursor and Codex, with a guard that checks Claude's commands before they run.
GitHub · TypeScript · 153 stars · 8 forks · 0 stars in 24 hours · Trending score 0.51
-
7
alifurkangokce/driftlint
Finds the claims in your CLAUDE.md / AGENTS.md / skills that your code no longer supports. Zero-config, no API key.
GitHub · TypeScript · 61 stars · 4 forks · +1 stars in 24 hours · Trending score 0.45
-
8
Heyvhuang/copybook-skills
Your coding agent picks the tip that fits the task. From @Voxyz_ai, in English and Chinese.
GitHub · Shell · 8 stars · 0 forks · +1 stars in 24 hours · Trending score 0.42
-
9
mrcbrbn5361/SyncytiumMD
AI agent workspace infrastructure: one canonical .syncytium/ context, adapters for 10+ AI coding tools, handoff baton, lease lock, CI drift gate, 3D knowledge graph and a 23-tool MCP server.
GitHub · TypeScript · 7 stars · 2 forks · 0 stars in 24 hours · Trending score 0.31
-
10
GeiserX/LynxPrompt
Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more
GitHub · TypeScript · 59 stars · 6 forks · 0 stars in 24 hours · Trending score 0.29
-
11
FramY2/ctxwise
Multi-agent context firewall, MCP schema tree-shaker, and token budget guard for Claude Code (CLAUDE.md), OpenAI Codex (AGENTS.md), and Cursor.
GitHub · TypeScript · 8 stars · 8 forks · 0 stars in 24 hours · Trending score 0.28
-
12
solanabr/ai-kit
Claude Code / Codex / AI configs for the expert Solana builder. CLAUDE.md, agents, commands, hooks, rules, skills and settings across Web, Anchor, Pinnochio, Unity, Mobile, security and more.
GitHub · Shell · 112 stars · 59 forks · 0 stars in 24 hours · Trending score 0.22
-
13
ciskonc/dsh-context-imports
Claude Code-style @path imports for DeepSeek Harness: expands @imports in AGENTS.md/CLAUDE.md and injects referenced files into context at session start
GitHub · TypeScript · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.10
-
14
V-Songbird/flint
🔥 Two drop-in text files that make Claude Code write less and talk less — a CLAUDE.md fragment and a prompt that tunes the rules you already have. Nothing to install.
GitHub · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
15
sohaibt/product-mode
The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.
GitHub · TypeScript · 162 stars · 6 forks · −14 stars in 24 hours · Trending score 0.09
-
16
umararshad4/honey-stack
Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.
GitHub · TypeScript · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
17
mohamedsabith/setupscore
Stop vibe-checking your CLAUDE.md. Benchmark it on your own code. Real commits. Hidden tests. One score out of 100.
GitHub · TypeScript · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
18
aunysillyme/agent-personalizer
AI custom instructions from approved entries: a profile and rules for Claude Code, Codex, Cursor, Gemini CLI, Hermes Agent and ChatGPT, kept in sync from one source.
GitHub · JavaScript · 14 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08
-
19
TurboKach/claude-code-setup
Claude Code setup: opinionated CLAUDE.md, a feature pipeline skill (plan → delegated execute → codex cross-review → ship), pinned role agents, parallel subagent fan-out, and a one-command installer with self-update.
GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
20
ilien-dev/muninn
Persistent memory for Claude Code and Codex CLI that never serves a replaced decision, and turns CLAUDE.md / AGENTS.md rules into permission rules and deny hooks. Local-first: one Rust binary, SQLite + FTS5, no cloud, no API key, no LLM in the read path. Cue-anchored recall under a 700-token budget.
GitHub · Rust · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
21
kgdemir/claude-agentic-os
Claude Agentic OS: portable Claude Code setup — global rules, plugin set, per-project memory, statusline and launcher, installed by one script.
GitHub · Shell · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
22
ArtVsMark/Engineering-Incidents-Playbook
Правила работы с Claude Code и конвейером GitHub — каждое с историей поломки, из которой выросло · Incident-based rules for Claude Code and GitHub: every rule grew out of a real failure, with the incident, the mechanism behind it, and where it does not apply.
GitHub · Python · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07
-
23
Antarsoft/morphness
Self-improving multi-agent harness for Claude Code. A Technical Lead plans, Full-stack builds, QA verifies, and retros turn lessons into rules that fit your project. Stack-agnostic.
GitHub · Shell · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.07
-
24
edvardgrishin27/nativeprompt
Проверяет промпты и файлы инструкций (CLAUDE.md, AGENTS.md, скиллы) по правилам вашей модели: Claude Fable 5.2, Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-6 и 6.1, Codex, Gemini CLI. Советует уровень усилий. Каждый совет со ссылкой на документацию вендора. Без API-ключей и зависимостей, офлайн.
GitHub · Python · 129 stars · 13 forks · 0 stars in 24 hours · Trending score 0.03