Borrowing it
Nothing to install: this file belongs to henryiii/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.
curl -O https://raw.githubusercontent.com/henryiii/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/henryiii/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/henryiii/skills/agents-md)<a href="https://agentmods.dev/instructions/henryiii/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/henryiii/skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/henryiii/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/henryiii/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00381 | $0.00381 |
| Opus 5.5 | $0.00152 | $0.00152 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
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 2mo 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.
What it actually says
Agent instructions
What this repo is
A collection of agent skills following the open https://agentskills.io specification, plus a few helper scripts. Skills are tested with OpenCode and open models (Kimi, GLM, Gemma), so write skill instructions to be harness- and model-agnostic — do not assume Claude-specific features. Note that some harnesses (like pi) don't tell the model what model it is, so skills that need a model name must derive it another way.
Structure
- Each skill is a top-level directory containing a
SKILL.mdwith YAML frontmatter:name,description,license, and optionallycompatibility(required tools, e.g. "Requires uv"). The body is step-by-step instructions for an agent. descriptionshould say when to trigger, phrased like "Use when dropping a Python version from a project".- Optional subdirectories:
resources/for docs the skill tells the agent to read on demand (seedrop-python/),assets/for files the skill copies into target repos (seesp-recommends/), andscripts/for helper scripts the skill runs (seeexplore-issues/). - Python scripts (top-level
scripts/and inside skills) use only the standard library — run withpython3directly; GitHub access goes through theghCLI. - The README lists every skill with a one-line summary; update it when adding or renaming a skill.
Conventions
- Skills consistently prefer
uv/uvxfor running Python tools andprek -a --quiet(a Rust pre-commit rewrite) for linting in target repos. - There is no build, test suite, or lint config in this repo itself.
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.
- 2mo ago First seen · 19 lines · 381 tokens per session scan A 2e378486986f
skills AGENTS.md is an instructions file published in the GitHub repository henryiii/skills (10 stars, last pushed 2d ago), licensed MIT. It adds 381 tokens to every session, about $0.0015 per session on Opus 5.5. 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.
skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills AGENTS.mdhenryiii/skills | Instructions file | 10 | 2d ago | MIT | A | 381 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 1,907 | GitHub Copilot |