What is cc-skills AGENTS.md?

Repository instructions for developing and maintaining Claude Code skills and plugins. They describe the folder layout, development setup, Git workflow, validation checks, and pull-request process.

Use them when adding or changing plugins, running tests and checks, following the repository's Git process, or preparing a pull request.

They give coding agents the project rules needed to make consistent changes and validate them before submission.

How rube-de/cc-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to rube-de/cc-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rube-de/cc-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/rube-de/cc-skills

Made for: Claude Code, Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/rube-de/cc-skills/agents-md.svg)](https://agentmods.dev/instructions/rube-de/cc-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/rube-de/cc-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/rube-de/cc-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 830 This file is loaded in full into every session.

When invoked 830 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00830	$0.00830
Opus 5	$0.00415	$0.00415
Sonnet 5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 7d ago against content hash 0052540d0159, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cc-skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Claude Code skills marketplace — plugins for multi-agent development, AI council reviews, CI code review, project management, plugin development, quality gates, and platform-specific tooling. See .claude-plugin/marketplace.json for the full plugin registry.

Plugin Architecture

Each plugin follows this structure:

plugin-name/
├── agents/       → Agent definitions (subagents, teammates)
├── commands/     → Slash commands (/plugin:command)
├── hooks/        → hooks.json (PreToolUse, PostToolUse, SessionStart)
├── scripts/      → Shell scripts for hooks and validation
└── skills/       → Bundled skills with SKILL.md + references/

See docs/PLUGIN-AUTHORING.md for the full authoring guide.

Dev Environment

Run bun install to install dependencies
Check the name field in package.json to confirm the correct package identity — skip the top-level one when looking at plugins
Plugin directories live under plugins/ — each is self-contained
Refer to .claude-plugin/marketplace.json as the single source of truth for all plugin metadata

Git Workflow

Always run git fetch origin && git pull origin main before planning or starting any work
Always create a fresh branch off remote main before editing: git checkout -b <branch-name> origin/main
Never commit directly to main
Use conventional commits (feat:, fix:, docs:, chore:, etc.) — semantic-release picks these up

Validation & PRs

CI plan lives in .github/workflows/ (ci.yml validates on PR, release.yml runs on push to main)
Run bun scripts/validate-plugins.mjs and fix any errors before committing — CI runs the same check
After adding or moving plugin directories or updating marketplace entries, re-run validation to catch orphaned plugin directories or missing source paths
PRs target main; semantic-release handles versioning on merge — never edit versions by hand
Prompt engineering review: When a change touches agent prompts (prompt: > blocks, SKILL.md instructions, *-workflow.md teammate prompts, agents/*.md), review it against known pitfalls in docs/learnings.md before creating the PR. Specifically check: no literal actions in preambles before numbered workflow gates, no dual numbered sequences, imperatives over aphorisms, and no terminology mismatches with existing workflow steps.

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 53 lines · 830 tokens per session scan A 0052540d0159

Subscribe to this mod's changes

cc-skills AGENTS.md is an instructions file published in the GitHub repository rube-de/cc-skills (10 stars, last pushed yesterday), licensed MIT. It adds 830 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Code review Git and workflow Multi-Agent Planning Productivity agent-teams ai-council claude-code-plugin

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

cc-skills: Instructions file for Claude Code