Borrowing it
Nothing to install: this file belongs to fellipeutaka/leon. 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/fellipeutaka/leon/main/AGENTS.mdgit clone --depth 1 https://github.com/fellipeutaka/leonWrote 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/fellipeutaka/leon/agents-md)<a href="https://agentmods.dev/instructions/fellipeutaka/leon/agents-md"><img src="https://agentmods.dev/badge/instructions/fellipeutaka/leon/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/fellipeutaka/leon/agents-md"><img src="https://agentmods.dev/badge/instructions/fellipeutaka/leon/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 | $0.00377 | $0.00377 |
| Opus 5.5 | $0.00151 | $0.00151 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
leon 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
Leon — Agent Skills Collection
Curated collection of Agent Skills for AI coding agents.
Project Structure
skills/— all skills (original and synced from upstream)scripts/sync-upstream.ts— syncs skills from external repos via GitHub APIupstream.json— manifest tracking which skills come from external repos, their source SHA and last sync timestamp
Skills Format
Each skill is a directory inside skills/ following the Agent Skills format:
SKILL.md(required) — skill definition with YAML frontmatter (name,description)README.md— user-facing documentationscripts/— helper scripts (optional)references/— supporting docs (optional)
Upstream Skills
Some skills are synced from external repos. Tracked in upstream.json.
- Sync all:
bun sync - Sync new only:
bun sync --new-only(skips skills that already have alastSync) - Sync one repo:
bun sync --repo mattpocock/skills - Sync one skill:
bun sync --repo mattpocock/skills --skill tdd - Synced skills can be locally modified — just know re-syncing overwrites local changes
- Set
GITHUB_TOKENenv var to avoid API rate limits
Tech Stack
- Bun + TypeScript
- No external dependencies
Conventions
- Skill directory names use kebab-case
- SKILL.md frontmatter must have
nameanddescriptionfields - Keep standalone skills self-contained — no relative cross-skill dependencies.
The Matt-derived flow variants listed in
downstream.jsonmay call their declared model-invoked dependencies through the Skill tool.
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 Changed · +4 lines · +69 tokens per session 923ca30074bf
- 2mo ago First seen · 39 lines · 308 tokens per session scan A ea04fc21146a
leon AGENTS.md is an instructions file published in the GitHub repository fellipeutaka/leon (5 stars, last pushed 2d ago), licensed MIT. It adds 377 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.
leon AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leon AGENTS.mdfellipeutaka/leon | Instructions file | 5 | 2d ago | MIT | A | 377 | 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 | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |