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/relai-ai/relai-sdk/agents-mdgit clone --depth 1 https://github.com/relai-ai/relai-sdkWrote 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/relai-ai/relai-sdk/agents-md)<a href="https://agentmods.dev/instructions/relai-ai/relai-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/relai-ai/relai-sdk/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 5.1 | $0.00609 | $0.00609 |
| Opus 5 | $0.00304 | $0.00304 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
relai-sdk 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 6d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The SDK lives in relai/, with subpackages such as critico, maestro, and mocker, plus shared clients in _client.py, simulator.py, and schema/. Tests sit in tests/ mirroring the package layout; add or extend fixtures in tests/conftest.py rather than scattering helpers. Reference agents and scripts belong in examples/. Documentation sources are under docs/ with theme overrides in docs_overrides/; site/ holds the rendered MkDocs build and dist/ captures published wheels.
Build, Test, and Development Commands
uv sync --group devinstalls runtime and development dependencies; rerun after editingpyproject.tomloruv.lock.uv run pytestexecutes the async-enabled suite; target a module withuv run pytest tests/relai/test_client.py.uv run pytest --cov=relai --cov-report=term-missingchecks coverage; keep touched modules at or above their prior baseline.uv run python -m buildproduces distribution artifacts indist/; clearbuild/if metadata changes before publishing.
Coding Style & Naming Conventions
Write Python 3.10+ code with four-space indentation and full type hints on public APIs. Modules stay lowercase_with_underscores, classes use PascalCase, and async helpers should read as verbs (get_user_query). Keep user-facing constants near their module entry points and export shared models from package __init__.py files for discoverability. Run ruff before committing; it autocorrects import order and blocks obvious runtime pitfalls.
Testing Guidelines
Pytest with pytest-asyncio backs all suites. Mark scope explicitly using @pytest.mark.unit or @pytest.mark.integration to keep filters meaningful. Favor fixtures in tests/conftest.py for shared clients, personas, and mock transport layers. For new evaluators or simulators, add async success and failure cases and confirm coverage with pytest --cov.
Commit & Pull Request Guidelines
Match the existing history with concise, imperative commit subjects (Fix link, Add tutorial) under 72 characters. Reference related issues or docs in the body. PRs should outline intent, affected subpackages, and validation steps (uv run pytest, uv run ruff format, uv run ruff check --fix). Attach screenshots or trace snippets when altering user-visible behavior, and wait for green CI before requesting merge.
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.
- 6d ago First seen · 23 lines · 609 tokens per session scan A f7625ea2d766
relai-sdk AGENTS.md is an instructions file published in the GitHub repository relai-ai/relai-sdk (102 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 609 tokens to every session, about $0.0030 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
hermeneutic AGENTS.md
AGENTS.md instructions for hermes-labs-ai/hermeneutic, covering agents.md — using hermeneutic from a coding agent, what this tool does, when to invoke it, programmatic use and calibration.
hermeneutic CLAUDE.md
Claude Code instructions for hermes-labs-ai/hermeneutic: Read AGENTS.md first — it is the canonical in-session protocol for coding agents using or modifying this repo, and everything there applies to Claude Code sessions too.
replayd AGENTS.md
Instructions for TaimoorKhan10/replayd, covering replayd — three agent examples, what replayd does, the four-step loop, 1. capture a run and 2. mark it as failed.
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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.