Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/chriscox/agent-skills/claude-mdgit clone --depth 1 https://github.com/chriscox/agent-skillsWrote 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.
[](https://agentmods.dev/instructions/chriscox/agent-skills/claude-md)<a href="https://agentmods.dev/instructions/chriscox/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/chriscox/agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01200 | $0.01200 |
| Opus 5 | $0.00600 | $0.00600 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
agent-skills CLAUDE.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Instructions for AI agents working on this repository.
What This Repo Is
A collection of reusable skills for AI coding agents (Claude Code, Codex, Gemini CLI, OpenClaw).
Each skill is a self-contained folder under skills/ with a SKILL.md and optional
supporting files.
Repo Structure
This repo is a Claude Code plugin marketplace and a standalone skill collection.
agent-skills/
├── .claude-plugin/
│ └── marketplace.json # Marketplace catalog (chriscox-skills)
├── skills/ # Canonical skill content (single source of truth)
│ └── <skill-name>/
│ ├── SKILL.md # Required: frontmatter + instructions
│ ├── <skill-name>.yml # Optional: config template for per-repo overrides
│ ├── issue-templates/ # Optional: GitHub issue form templates
│ └── templates/ # Optional: doc scaffolding templates
├── plugins/ # Claude Code marketplace wrappers
│ └── <skill-name>/
│ ├── .claude-plugin/plugin.json # Per-plugin manifest
│ └── skills/<skill-name> → # Symlink to ../../skills/<skill-name>
├── skills.json # Machine-readable skill index (keep in sync)
└── install.sh # Multi-platform installer (Codex, Gemini CLI, OpenClaw)
Marketplace vs Standalone
- As a marketplace (Claude Code): users add with
/plugin marketplace add chriscox/agent-skills, then install individual plugins with/plugin install <name>@chriscox-skills. Plugins use symlinks to the canonicalskills/directory; Claude Code follows symlinks during copy. - As standalone skills (Codex, Gemini CLI, OpenClaw): install via
install.sh, native installer (gemini skills install), or manual copy. Usesskills/directly.
Conventions
Adding a New Skill
- Create
skills/<skill-name>/SKILL.mdwith proper frontmatter (name+description) - If the skill has per-repo config, add
<skill-name>.ymlat the skill root - If the skill provides GitHub issue templates, add them to
issue-templates/ - If the skill provides doc templates, add them to
templates/ - Create the marketplace plugin wrapper:
plugins/<skill-name>/.claude-plugin/plugin.json— manifest with"skills": "./skills/"plugins/<skill-name>/skills/<skill-name>— symlink to../../../skills/<skill-name>
- Add the plugin to
.claude-plugin/marketplace.jsonwith name, source, and description - Update
skills.jsonwith the new skill entry - Update the
README.md:- Add to the skills table of contents
- Add a full section with: problem, what it does, prerequisites, config, example
- Update the skills count badge
- Test with
./install.sh list,./install.sh skill <name>, and./install.sh templates <name>
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.
- 5d ago First seen · 122 lines · 1,200 tokens per session scan A 3276e38a15fe
agent-skills CLAUDE.md is an instructions file published in the GitHub repository chriscox/agent-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 1,200 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
kmux AGENTS.md
AGENTS.md instructions for kkd927/kmux, covering agents.md, kmux focus and test discipline.
surreal-skills AGENTS.md
Instructions for 24601/surreal-skills, covering agent briefing: surrealdb, quick start, check if configured, get full capabilities manifest (json) and capabilities.
template GEMINI.md
Instructions for ai-plugin-marketplace/template, covering skill evaluator, usage and how it works.
roblox-ai-workflow CLAUDE.md
Claude Code instructions for schmusch/roblox-ai-workflow, covering roblox ai-workflow — claude code entry point, kanonischer doku-index & ki-einstieg, quellenrang (source of truth hierarchy), neue ideen & feature-pipeline (ideen-handoff) and what this workspace is for.
roblox-ai-workflow AGENTS.md
AGENTS.md instructions for schmusch/roblox-ai-workflow, covering kanonischer doku-index & ki-einstieg, quellenrang (source of truth hierarchy), neue ideen & feature-pipeline (ideen-handoff), how to use skills here and canonical workflow.
roblox-ai-workflow GEMINI.md
Gemini CLI instructions for schmusch/roblox-ai-workflow, covering roblox ai-workflow — gemini cli entry point, kanonischer doku-index & ki-einstieg, quellenrang (source of truth hierarchy), neue ideen & feature-pipeline (ideen-handoff) and skill activation.