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/imbios/relay/agents-mdgit clone --depth 1 https://github.com/ImBIOS/relayWhat 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 | $0.01340 | $0.01340 |
| Opus 5 | $0.00670 | $0.00670 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
relay 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Relay
Project Overview
Relay is a CLI for managing AI API providers (Z.AI, MiniMax) with a built-in HTTP proxy for seamless ForgeCode integration. It enables hot-switching providers without restarting sessions.
Tech Stack
- Runtime: Bun 1.2.0+
- Language: TypeScript (ESM, strict)
- CLI Framework: oclif + Ink (React-based terminal UI)
- Linting: oxlint + oxfmt (OXC)
- Testing: Bun test runner
Architecture
src/
├── cli.ts # CLI entry point
├── run.ts # Main runner
├── commands/ # CLI commands (proxy, account, hooks, auto, usage, doctor)
├── config/ # accounts-config.ts (primary), settings.ts (legacy compat)
├── proxy/ # HTTP proxy server
├── providers/ # Provider definitions (Z.AI, MiniMax)
├── sdk/ # SDK for programmatic access (community-maintained)
├── tests/integration/ # Docker-isolated integration tests
├── utils/ # Logger, telemetry, format, validation
└── ui/ # Ink UI components
Support Policy
Officially supported features (maintained by @ImBIOS):
- Proxy server (
relay proxy start/stop/status) - Account management (
relay account add/list/switch/edit/remove/migrate-names) - ForgeCode hooks (
relay hooks forge-setup,relay hooks forge-stop) - Codex CLI hooks (
relay hooks codex-setup,relay hooks codex-stop) - Claude Code hook integration (
relay hooks session-start,relay hooks install/uninstall/status) - Usage & diagnostics (
relay usage,relay doctor) - Auto-rotation (
relay auto enable/disable/status) - Telemetry & analytics (
relay analytics)
Community-maintained features:
These are provided as-is. Breaking changes are acceptable. Contributors from those tools' communities are welcome to submit fixes. Files are marked with COMMUNITY-MAINTAINED header comments.
- OpenCode integration (
relay opencode) - Direct Claude CLI wrapper (
relay claude) - Session-end commit prompt (
relay hooks stop) - SDK (
src/sdk/index.ts)
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 · 129 lines · 1,340 tokens per session scan A 8a4f4827e5e9
relay AGENTS.md is an instructions file published in the GitHub repository ImBIOS/relay (9 stars, last pushed 2mo ago), licensed MIT. It adds 1,340 tokens to every session, about $0.0067 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
rosetta pr-review-bots.instructions.md
How Copilot and CodeRabbit reviews manifest on a rosetta PR, why each looks different from a gh point of view, and what 'wrapping a PR' actually requires.
rosetta CLAUDE.md
Instructions for tikoci/rosetta, covering rosetta, project documentation, where does this go?, instruction routing and fast pointers.
rosetta extractor-import-side-effects.instructions.md
Every extractor entrypoint must run its side effects only under import.meta.main. Top-level db.ts imports still open a real DB connection, so tests must import extractors safely.
rosetta local-db-grounding.instructions.md
In a checkout, the resolved ros-help.db is untrusted until verified; the latest CI release DB is the grounding source of truth.
rosetta database.instructions.md
Use when working on SQLite schema, database initialization, WAL mode, FTS5 triggers, or table definitions.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.