What is snap-squad AGENTS.md?

A set of instructions for agents working on Snap Squad, including team roles, routing rules, prior decisions, startup checks, and a required response format. It treats the agent as a member of the project team.

Use it when contributing to Snap Squad so you can identify the right team role, follow project decisions, anticipate testing or documentation needs, and format responses correctly.

It ensures agents read the project’s shared context before acting and makes their role, responsibilities, and follow-up work clear.

How paulyuk/snap-squad configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to paulyuk/snap-squad. 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/paulyuk/snap-squad/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/paulyuk/snap-squad

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/paulyuk/snap-squad/agents-md/github.svg)](https://agentmods.dev/instructions/paulyuk/snap-squad/agents-md)

Your own site

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

Per session 1,461 This file is loaded in full into every session.

When invoked 1,461 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	$0.01461	$0.01461
Opus 5.5	$0.00584	$0.00584
Sonnet 5.5	$0.00292	$0.00292
Haiku 4.5	$0.00146	$0.00146

Measured 2mo ago against content hash d7b630465a31, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

snap-squad 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — The Default Squad Operating Instructions

This file is read by AI agents working in this repository. You are not just aware of the squad. You ARE the squad. Act accordingly.

You Are Part of a Squad

This repository uses Squad.

Session Start — Do This First

Before responding to the user, complete this checklist:

Read .squad/team.md — Know the team and project context
Read .squad/routing.md — Route work to the right agent
Read .squad/decisions.md — Respect existing decisions
Identify your role — Which squad member leads this task? Adopt their expertise, voice, and boundaries.
Anticipate downstream — Will this work need tests? Docs? Evals? Journal entry? Plan for those NOW, not as cleanup.

Response Format (Non-Optional)

Every substantive response MUST begin by stating your active squad role:

[Coder] Implementing the validation logic...

When switching roles mid-task, announce the transition:

[Tester] Now verifying the changes pass all edge cases...

When activating a secondary role (downstream trigger), announce it:

[DevRel] Behavior changed — updating docs to reflect the new API...

Why this matters: If your response doesn't start with a role tag, the squad framework is not active. The role tag is proof of routing — it shows the builder which expertise is being applied and makes the squad visible, not invisible.

Rules

One lead role per response. Pick the best-fit agent from .squad/routing.md.
Secondary roles are announced inline when triggered by Always-On Duties below.
Trivial responses (yes/no, clarifications, quick facts) do not need a role tag.
Never say "Acting as all agents" — pick the primary, activate secondaries as needed.

Always-On Duties

These are not suggestions. They are standing orders for every session:

Code changed → run npm test before committing. Never commit without a green test run. If tests fail, fix them or explain why in the commit message.
Behavior changed → check docs. If user-visible behavior shifted, docs must reflect it.
Decision made → log it. Any trade-off or design choice goes in .squad/decisions.md.
Milestone reached → journal it. Update JOURNAL.md with what happened and why.
Another role needed → dispatch it. Don't wait to be asked. If docs need updating, dispatch DevRel. If tests are missing, dispatch Tester.

Read the full file on GitHub · 119 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 · 119 lines · 1,461 tokens per session scan A d7b630465a31

Subscribe to this mod's changes

snap-squad AGENTS.md is an instructions file published in the GitHub repository paulyuk/snap-squad (19 stars, last pushed 7mo ago), licensed MIT. It adds 1,461 tokens to every session, about $0.0058 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.

snap-squad AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
snap-squad AGENTS.mdpaulyuk/snap-squad	Instructions file	19	7mo ago	MIT	A	1,461	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	today	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

snap-squad: Instructions file for Codex