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/gxdevs/grouter/agents-mdgit clone --depth 1 https://github.com/GXDEVS/grouterWhat 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 | $0.01703 | $0.01703 |
| Opus 5 | $0.00851 | $0.00851 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
grouter 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project
grouter (package grouter-auth) is a CLI + local OpenAI-compatible proxy that aggregates OAuth and API-key accounts across 15+ AI providers (Qwen, GitHub Copilot, Codex, Codex, Gemini, Kimi, Kiro, KiloCode, GitLab Duo, Cursor, OpenRouter, Groq, DeepSeek, etc.) behind a single local endpoint. Built as a Bun single-file binary — no external services, state lives in ~/.grouter/grouter.db (SQLite).
Commands
bun run dev # bun --hot index.ts serve fg (foreground, hot-reload)
bun run start # Foreground proxy (no hot-reload)
bun run build # Pre-embeds logos, bundles to dist/grouter (chmod +x)
bun run deploy # build + bun link — refresh the globally-linked binary
bun test # Run Bun tests (none currently — add alongside code)
bun test path/to/file.test.ts # Single test file
# CLI (once built + linked, or via `bun index.ts <cmd>`)
grouter setup # First-run wizard
grouter add # Arrow-key picker → add a provider connection
grouter serve on|off|fg|logs|restart|status
grouter models [provider]
grouter up openclaude [--provider X --model Y]
grouter list | test [id] | enable/disable <id> | remove <id> | unlock [id]
grouter config [--strategy fill-first|round-robin] [--port N] [--sticky-limit N]
The prebuild script (scripts/embed-logos.ts) reads src/public/logos/*.png and emits src/web/logos-embedded.ts with base64 constants — this is what makes logos work inside the single-file bundled binary. Never edit logos-embedded.ts by hand.
Architecture
Entry point and command layer
index.ts wires commander subcommands to handlers in src/commands/*.ts. The hidden _daemon subcommand is the entrypoint the detached background proxy spawns — never call it directly.
Proxy server (src/proxy/)
serve on spawns a detached child (_daemon) that runs startAllServers():
- Router on
:3099(configurable) — picks any active account across all providers using the rotation strategy. - Per-provider listeners on
:3100+— each provider with registered accounts gets its ownBun.serveinstance that pins the provider on every request. Port allocation lives in theprovider_portstable.
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.
- 2d ago First seen · 90 lines · 1,703 tokens per session scan A c5974661452d
grouter AGENTS.md is an instructions file published in the GitHub repository GXDEVS/grouter (55 stars, last pushed 4d ago), licensed MIT. It adds 1,703 tokens to every session, about $0.0085 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.