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/heristop/leclap/agents-mdgit clone --depth 1 https://github.com/heristop/leclapWrote 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/heristop/leclap/agents-md)<a href="https://agentmods.dev/instructions/heristop/leclap/agents-md"><img src="https://agentmods.dev/badge/instructions/heristop/leclap/agents-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 | $0.02378 | $0.02378 |
| Opus 5 | $0.01189 | $0.01189 |
| Sonnet 5 | $0.00476 | $0.00476 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
leclap 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in the leclap monorepo. This is the canonical, tool-agnostic agent guide. Read it first.
Project overview
A template-based, cross-platform FFmpeg video composer. A JSON template describes a video's structure (sections, filters, music); the engine compiles it into a finished video. The same core runs on Node.js, in the browser (WebAssembly), and in React Native.
- High-level intro:
README.md - Design system (brand, colors, typography):
DESIGN.md - Architecture & design patterns:
docs/architecture.md - Template JSON reference:
docs/template-configuration.md - Engine configuration (ProjectConfig, env vars, encoder tiers):
docs/engine-configuration.md - FFmpeg detection/fallback:
docs/architecture.md
Repository layout
pnpm workspaces (apps/*, packages/*); no turbo/nx. The repo root is a private orchestrator (leclap) holding only shared dev tooling and scripts — not a publishable package. The published artifacts are ffmpeg-video-composer (the engine), @leclap/cli (the leclap command), and @leclap/mcp; the rest is private.
| Path | Package | What it is |
|---|---|---|
. |
leclap (private) |
Workspace root — shared tooling (vp, vitest) and orchestration scripts only. |
packages/ffmpeg-video-composer |
ffmpeg-video-composer |
The composition library (programmatic API), Node + browser/WASM. The heart of the repo. |
packages/leclap-cli |
@leclap/cli |
The leclap CLI (citty): init scaffolder, render, diagnose. Consumes ffmpeg-video-composer. |
packages/leclap-mcp |
@leclap/mcp |
MCP server exposing the engine as agent-callable tools (schema/validate/compose/probe) over stdio. Consumes ffmpeg-video-composer. |
packages/ffmpeg-engine |
(cargo crate) | Embedded FFmpeg engine (Rust + uniffi) for on-device compiles; built via scripts/ffmpeg/. |
apps/leclap-expo |
@leclap/expo |
Expo / React Native app — on-device native-engine compiles, Tamagui UI (reference). |
apps/leclap-web |
@leclap/web |
React 19 + Vite + Tailwind web app — in-browser FFmpeg via WASM (reference). |
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.
- 4d ago First seen · 97 lines · 2,378 tokens per session scan A bd31284e7e21
leclap AGENTS.md is an instructions file published in the GitHub repository heristop/leclap (24 stars, last pushed 8d ago), licensed MIT. It adds 2,378 tokens to every session, about $0.0119 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 2026-08-30.
Other instructions, from other repositories
uniwind AGENTS.md
AGENTS.md instructions for uni-stack/uniwind, covering agent instructions and checks.
react-native CLAUDE.md
Claude Code instructions for storybookjs/react-native, covering development commands, initial setup, development, story generation and testing.
clarity AGENTS.md
AGENTS.md instructions for SchroederNathan/clarity, covering expo has changed, the design system, extracting a component, auditing for drift and typography: sf pro rounded.
react-native-boilerplate CLAUDE.md
Claude Code instructions for wataru-maeda/react-native-boilerplate, covering claude ai development guide, project context, always use these built-in features, configuration & environment and theme & styling.
expo-targets AGENTS.md
AGENTS.md instructions for csark0812/expo-targets, covering agents, product posture, sealed zones, docs ssot and safe commands.
expo_boilerplate CLAUDE.md
Claude Code instructions for chohra-med/expo_boilerplate, covering claude.md — mobilelauncher lt, 🌿 branches — the trunk is development, there is no main, project skill, what this project is and the master rules.