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/animeshkundu/github-router/agents-mdgit clone --depth 1 https://github.com/animeshkundu/github-routerWhat 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 | $0.00443 | $0.00443 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
github-router 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 3d 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
github-router
A reverse proxy that exposes GitHub Copilot as OpenAI and Anthropic compatible API endpoints.
Build, Lint, and Test Commands
- Build:
bun run build(uses tsdown) - Dev:
bun run dev - Lint:
bun run lint(uses typescript-eslint + eslint-config-prettier) - Lint all:
bun run lint:all - Lint & Fix staged files:
bunx lint-staged - Test all:
bun test - Test single file:
bun test tests/create-chat-completions.test.ts - Typecheck:
bun run typecheck - Start (prod):
bun run start
Code Style Guidelines
- Imports:
Use ESNext syntax. Prefer absolute imports via
~/*forsrc/*(seetsconfig.json). - Formatting:
Follows Prettier (with
prettier-plugin-packagejson). Runbun run lintto auto-fix. - Types:
Strict TypeScript (
strict: true). Avoidany; use explicit types and interfaces. - Naming:
Use
camelCasefor variables/functions,PascalCasefor types/classes. - Error Handling:
Use explicit error classes (see
src/lib/error.ts). Avoid silent failures. - Unused:
Unused imports/variables are errors (
noUnusedLocals,noUnusedParameters). - Switches: No fallthrough in switch statements.
- Modules: Use ESNext modules, no CommonJS.
- Testing:
Use Bun's built-in test runner. Place tests in
tests/, name as*.test.ts. - Linting:
Uses
typescript-eslint+eslint-config-prettier. Includes TypeScript-aware linting and consistent formatting. - Paths:
Use path aliases (
~/*) for imports fromsrc/.
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.
- 3d ago First seen · 50 lines · 443 tokens per session scan A 4132fa46d2f5
github-router AGENTS.md is an instructions file published in the GitHub repository animeshkundu/github-router (5 stars, last pushed 3d ago), licensed MIT. It adds 443 tokens to every session, about $0.0022 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 2026-08-31.
Other instructions, from other repositories
wyoming_openai AGENTS.md
Instructions for roryeckel/wyoming_openai, covering agents.md, project overview, development commands, testing and install development dependencies.
wyoming_openai CLAUDE.md
Instructions for roryeckel/wyoming_openai, a project described as: OpenAI-Compatible Proxy Middleware for the Wyoming Protocol.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
apm python.instructions.md
Python development guidelines.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.