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/rocketchat/opensource-contribution-leaderboard/agents-mdgit clone --depth 1 https://github.com/RocketChat/Opensource-Contribution-LeaderboardWrote 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/rocketchat/opensource-contribution-leaderboard/agents-md)<a href="https://agentmods.dev/instructions/rocketchat/opensource-contribution-leaderboard/agents-md"><img src="https://agentmods.dev/badge/instructions/rocketchat/opensource-contribution-leaderboard/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 | $0.01026 | $0.01026 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
Opensource-Contribution-Leaderboard 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 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Agents — Opensource Contribution Leaderboard
This file provides context for any AI coding agent (Copilot, Cursor, Windsurf, Cline, Aider, etc.) working on this project.
Quick Orientation
| What | Where |
|---|---|
| Frontend entry | src/index.js |
| Frontend HTML | index.html |
| Backend server | src/server/app.js |
| GitHub data fetcher | src/server/refresh.js |
| GitHub API wrapper | src/server/util/API.js |
| Utility helpers | src/server/util/Util.js |
| Config template | src/server/config-example.json |
| Live config (gitignored) | src/server/config.json |
| Admin panel | admin/ (separate webpack build) |
| Webpack config (main) | build/webpack.config.js |
| Webpack config (admin) | admin/build/webpack.config.js |
| REST API docs | REST-API.md |
| Cached leaderboard data | src/assets/data/data.json (auto-generated) |
npm Scripts
| Command | What it does |
|---|---|
npm run add |
Installs dependencies for root, server, and admin |
npm start |
Dev mode — webpack-dev-server with hot reload on :8080 |
npm run serve |
Starts the backend server (run in separate terminal during dev) |
npm run build |
Production build — compiles admin + main frontend |
npm run lint |
ESLint |
How It Works (in plain english)
app.jsstarts an Express server on port 8080- It spawns
refresh.jsas a child process refresh.jsreadsconfig.json, loops through thecontributorsarray, and calls the GitHub API for each one- Results are written to
src/assets/data/data.json - The frontend fetches
/dataendpoint which servesdata.json - Real-time updates via socket.io
- The API endpoints (
/api/stats,/api/rank,/api/contributor) read from the samedata.json
Critical Design Decisions
Hidden Rank Column
The rank column and some aggregate stats are rendered with invisible/white text. This is intentional — admins can select-all and copy the table to get full stats in one stroke. Do not "fix" this visibility.
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 · 114 lines · 1,026 tokens per session scan A 43b99152dcdd
Opensource-Contribution-Leaderboard AGENTS.md is an instructions file published in the GitHub repository RocketChat/Opensource-Contribution-Leaderboard (49 stars, last pushed 4mo ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 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
sigrank-mcp AGENTS.md
AGENTS.md instructions for SunrisesIllNeverSee/sigrank-mcp, covering sigrank mcp — agent rules, quick reference, publishing, master canon context (search authority) and when to load canon context.
platform AGENTS.md
AGENTS.md instructions for doka-guide/platform, covering agents.md — как работать с платформой доки, 1. правила работы, сначала подумай, потом пиши, минимум кода and правки хирургические.
zapo CLAUDE.md
Instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.
OSS-Skills CLAUDE.md
Instructions for chiruu12/OSS-Skills, covering oss-skills development, project structure, skill format, core principle and skill interconnection.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.