What is alloy AGENTS.md?

A quick-start guide for coding agents working in the Alloy repository, covering safety rules, setup, commands, examples, documentation, and testing profiles.

It helps agents create the development environment, run fast or full checks, execute tests, lint and format code, type-check it, and run provider examples.

It reduces setup mistakes and keeps changes small, reversible, tested, formatted, and free of secrets.

How lydakis/alloy configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to lydakis/alloy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lydakis/alloy/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/lydakis/alloy

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lydakis/alloy/agents-md/github.svg)](https://agentmods.dev/instructions/lydakis/alloy/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lydakis/alloy/agents-md"><img src="https://agentmods.dev/badge/instructions/lydakis/alloy/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lydakis/alloy/agents-md"><img src="https://agentmods.dev/badge/instructions/lydakis/alloy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,397 This file is loaded in full into every session.

When invoked 2,397 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02397	$0.02397
Opus 5.5	$0.00959	$0.00959
Sonnet 5.5	$0.00479	$0.00479
Haiku 4.5	$0.00240	$0.00240

Measured 2mo ago against content hash d1c39f348d34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

alloy 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 2mo 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.

AGENTS.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS — Quick Guide

This file guides coding agents working in this repository. It applies to the entire repo. Deeper AGENTS.md files may further specialize instructions and take precedence within their subtrees.

Scope & Expectations

Keep changes minimal, focused, and reversible; avoid broad refactors.
Do not alter public API without explicit instruction; prefer additive changes.
Never commit secrets (.env, API keys). Verify .gitignore is respected.
Follow style tools; let formatters fix whitespace vs. hand edits.

One‑Time Setup

Create env: python -m venv .venv && source .venv/bin/activate
Install dev deps: pip install -e '.[dev]'
Install hooks: pre-commit install

Core Commands

Quick check: make ci-fast (lint + typecheck + focused tests, coverage >= 80)
Full local CI: make ci (lint, typecheck, tests)
Tests: make test (filter: pytest -k <pattern> -q)
Lint/format: make lint / make format then make precommit
Typecheck: make typecheck
Examples (fake backend): make examples-quick
Provider examples (need keys): make examples-openai|anthropic|gemini|ollama
Docs: make docs-serve (live) or make docs-build (strict)
Release (trusted publishing): create and push a tag, see make release

Testing Profiles

Unit/contracts/providers: make ci-fast
Integration (requires keys): make itest or provider‑specific make itest-openai|anthropic|gemini|ollama
Skip integ locally: ALLOY_IT_MODEL=none pytest -q
Smoke examples without keys: make smoke-examples (uses ALLOY_BACKEND=fake)

Environment Cheatsheet

Default model: gpt-5-mini (override with ALLOY_MODEL)
Useful vars: ALLOY_TEMPERATURE, ALLOY_MAX_TOKENS, ALLOY_SYSTEM/ALLOY_DEFAULT_SYSTEM, ALLOY_RETRY, ALLOY_MAX_TOOL_TURNS, ALLOY_EXTRA_JSON
Provider keys: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY; use .env locally and dotenv -f .env run -- <cmd>

Code & Docs Style

Python: PEP 8 + type hints; 4‑space indent. Run ruff and black.
Docstrings: concise, imperative; include non‑obvious types.
Imports: re‑export public API from alloy/__init__.py; import via from alloy import ... in code/docs.
Decorators: bare @command/@tool when no options; @command(...)/@tool(...) when passing options.

Read the full file on GitHub · 140 lines

Changes

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.

2mo ago First seen · 140 lines · 2,397 tokens per session scan A d1c39f348d34

Subscribe to this mod's changes

alloy AGENTS.md is an instructions file published in the GitHub repository lydakis/alloy (19 stars, last pushed 5mo ago), licensed MIT. It adds 2,397 tokens to every session, about $0.0096 per session on Opus 5.5. 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.

agent-framework ai-agents anthropic dataclasses function-calling gemini-ai

alloy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
alloy AGENTS.mdlydakis/alloy	Instructions file	19	5mo ago	MIT	A	2,397	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

alloy: Instructions file for Codex