Borrowing it
Nothing to install: this file belongs to natuleadan/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/natuleadan/skills/main/AGENTS.mdgit clone --depth 1 https://github.com/natuleadan/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/natuleadan/skills/agents-md)<a href="https://agentmods.dev/instructions/natuleadan/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/natuleadan/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/natuleadan/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/natuleadan/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 | $0.01296 | $0.01296 |
| Opus 5.5 | $0.00518 | $0.00518 |
| Sonnet 5.5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Natuleadan Skills: Agent Guide
Technical guide for working in this repository. The README is the product overview.
Requirements
- Node.js 24 or newer, which runs TypeScript entry points directly.
- pnpm 12.
- No Python: validation, hooks and CI run on Node.
Commands
| Command | What it does |
|---|---|
pnpm validate |
full validation: skills, audit, notices and scripts |
pnpm validate:skills |
skills, audit and script freshness |
pnpm industry |
audit the sixteen industry skills |
pnpm notices |
regenerate ThirdPartyNotices.txt |
pnpm scripts:generate |
regenerate every skill script stub |
pnpm scripts:check |
verify stubs and run their smoke tests |
pnpm md:check |
reject spaced hyphens in Markdown prose |
pnpm badges |
regenerate README counts |
pnpm badges:check |
verify counts in README |
pnpm skill <name> |
run skills/<name>/scripts/main.ts |
pnpm release:plan |
show the next version from commits |
pnpm release:prepare |
write version, manifests and changelog |
pnpm release:check |
verify the version matches the commits |
pnpm changelog:check |
verify changelog versions, sections and tags |
pnpm check-plugin-version |
verify plugin manifests match package.json |
Project structure
| Path | Purpose |
|---|---|
skills/<name>/SKILL.md |
frontmatter and instructions |
skills/<name>/metadata.json |
version, abstract, references |
skills/<name>/references/ |
prose notes with mermaid diagrams |
skills/<name>/scripts/main.ts |
generated entry point, required |
tools/ |
validator, industry audit, notices and skill runner |
.claude-plugin/ |
marketplace and plugin manifests |
Development
Clone the repository and run pnpm install; the prepare script installs the
Husky hooks. Use pnpm validate as the single gate before pushing.
Validation
pnpm validate enforces:
- Frontmatter and directory names match.
- Every declared reference exists and has a mermaid sequence diagram.
- No fenced code blocks in markdown except mermaid.
- No spaced hyphen
-in Markdown prose; the only exception is the copyright line2023 - Present.. - No
code/, no executables and no Python. scripts/starts atmain.tsand holds only TypeScript or ESM.- Every skill is registered in both plugin manifests.
- License and version match across manifests.
ThirdPartyNotices.txtmatches the installed dependencies.- Every skill has a generated
scripts/main.tsand passes the smoke test. - README badges match the skill, reference and script counts.
- The version matches the commits since the last tag.
- Changelog versions, sections and past tags are consistent.
- Industry skills stay neutral: no platform concepts, vendor names or pricing.
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.
- 10d ago Changed · +77 lines · +853 tokens per session b126e81018e3
- 1mo ago Changed · +34 lines · +302 tokens per session 1b6a82db1454
- 2mo ago First seen · 17 lines · 141 tokens per session scan A 02adccb30b61
skills AGENTS.md is an instructions file published in the GitHub repository natuleadan/skills (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,296 tokens to every session, about $0.0052 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.mdnatuleadan/skills | Instructions file | 4 | 6d ago | Apache-2.0 | A | 1,296 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |