AGENTS.md is agent-read markdown (agents) from rtur2003/claude-code-promts-skills.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# AGENTS.md
## Project Overview
- **Name**: Claude Code Prompts
- **Type**: Prompt library (Markdown-first) plus tested scripts bundled as Claude Code and cross-agent skills (`.claude/skills/`, `.agents/skills/`) and safety hooks
- **Purpose**: Production-ready system prompts for Claude Code, with cross-agent discovery through `AGENTS.md`, `.agents/skills/`, and `llms.txt`
- **Core Methodology**: APEI cycle — Analyze → Plan → Execute → Iterate
- **License**: MIT
- **Language**: English only
## Routing skill
`.claude/skills/find-prompt/SKILL.md` is the canonical routing table. `.agents/skills/find-prompt/SKILL.md` is a thin cross-agent adapter. Keep the canonical table, indexes, `llms.txt`, and eval cases in sync whenever a prompt is added, removed, or renamed.
## Repository Structure
```
├── AGENTS.md # This file — project memory
├── README.md # Main catalog, portfolio table, common combinations
├── REPOSITORY-MAP.md # 30-second orientation, task -> file lookup
├── QUICK-START.md # 30-second setup guide
├── USAGE.md # Scenario-based prompt composition
├── CONTRIBUTING.md # Contribution guidelines
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_bioxhxlac46yxnmc
GET https://markdownregistry.com/api/v1/resolve?ref=rtur2003/claude-code-promts-skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/6a052904be3f032dfd9cc834df81716d2c2a9f4fe047d2074c4bd5ae4f3721d8
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
rtur2003/claude-code-promts-skills · .agents/skills/capability-audit/SKILL.md · Use when evaluating, comparing, installing, or recommending a Claude Code plugin, Agent Skill, MCP server, agent…
rtur2003/claude-code-promts-skills · .agents/skills/changelog-from-commits/SKILL.md · Use when cutting a release, writing a CHANGELOG entry, or summarizing what changed since a tag — when the repo's…
rtur2003/claude-code-promts-skills · .agents/skills/deterministic-checks/SKILL.md · Use before committing, opening a PR, or reporting a task done — when you want ground-truth confirmation there are no…
rtur2003/claude-code-promts-skills · .agents/skills/doc-link-audit/SKILL.md · Use before publishing documentation, merging a docs PR, or reporting a Markdown-heavy repo's navigation as complete —…
rtur2003/claude-code-promts-skills · .agents/skills/find-prompt/SKILL.md · Use when the user names a coding, Claude Code, research, documentation, or technology-selection task; asks which prompt…
rtur2003/claude-code-promts-skills · .agents/skills/skill-audit/SKILL.md · Use when a skill isn't triggering as expected, before adding a new skill (to check for a name collision), during…
rtur2003/claude-code-promts-skills · .claude/skills/capability-audit/SKILL.md · Use when evaluating, comparing, installing, or recommending a Claude Code plugin, Agent Skill, MCP server, agent…
rtur2003/claude-code-promts-skills · .claude/skills/changelog-from-commits/SKILL.md · Use when cutting a release, writing a CHANGELOG entry, or summarizing what changed since a tag — when the repo's…
rtur2003/claude-code-promts-skills · .claude/skills/deterministic-checks/SKILL.md · Use before committing, opening a PR, or reporting a task done — when you want ground-truth confirmation there are no…
rtur2003/claude-code-promts-skills · .claude/skills/doc-link-audit/SKILL.md · Use before publishing documentation, merging a docs PR, or reporting a Markdown-heavy repo's navigation as complete —…
rtur2003/claude-code-promts-skills · .claude/skills/find-prompt/SKILL.md · Use when the user names a coding or Claude Code task ("add OAuth", "set up hooks", "review this PR", "pick a model")…
rtur2003/claude-code-promts-skills · .claude/skills/skill-audit/SKILL.md · Use when a skill isn't triggering as expected, before adding a new skill (to check for a name collision), during…
