What is Cougr AGENTS.md?

A repository instruction file for AI coding agents and developers working on the Cougr project. It defines required checks, review habits, branch-update steps, and project-specific commands.

Use it when changing Cougr code, before committing or pushing, and before opening a pull request. It covers running checks, applying automatic fixes, reading the complete diff, and keeping the branch current.

It prevents changes from being pushed or reported as complete while the project's checks are failing. It also makes the expected relationship between local checks, the diff, and continuous integration explicit.

How salazarsebas/Cougr configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to salazarsebas/Cougr. 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/salazarsebas/Cougr/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/salazarsebas/Cougr

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/salazarsebas/cougr/agents-md/github.svg)](https://agentmods.dev/instructions/salazarsebas/cougr/agents-md)

Your own site

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

Per session 605 This file is loaded in full into every session.

When invoked 605 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	$0.00605	$0.00605
Opus 5.5	$0.00242	$0.00242
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured today against content hash f18591b80531, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Cougr 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 today.

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 · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents (Codex, Cursor, Copilot, Claude Code, Gemini, and others) working on Cougr. If you are a person, this is also the shortest path to a pull request that gets merged.

The one rule

Run make check from the repository root before every commit you push. Fix everything it reports and run it again until the last line says All checks passed. It runs the same checks as CI for the parts of the repository you changed. A pull request is only merged when every CI workflow passes.

make fix applies the automatic fixes (formatting, docs site sync).
make check-all runs every check.
If a tool is missing, make check says how to install it. A skipped check still runs in CI.
CI tests your branch merged into main, so keep it current: git fetch upstream && git rebase upstream/main. Add the remote once with git remote add upstream https://github.com/salazarsebas/Cougr.git.

Do not report a task as done, and do not open a pull request, while make check fails.

Read your own diff before you push

Run git diff upstream/main...HEAD --stat, then read the full diff. Delete anything that is not part of the fix:

Files the issue does not need.
Generated output: target/, *.wasm, logs, coverage reports, build folders.
Encoded or minified content. A source file must be readable source code, never base64 or one giant line.
Editor, agent, or scratch files: plans, notes, TODO lists, .cursor/, .aider*.
Placeholder code: todo!(), unimplemented!(), empty function bodies, commented-out blocks.

Write files with normal editor or file tools. Never paste an API response or encoded content into a source file.

Scope

One issue per pull request. Do what the issue asks and nothing more.
You must be assigned to the issue before opening the pull request.
Put Closes #<issue> in the pull request description.
Commits follow Conventional Commits: <type>(<scope>): <summary>.

Project conventions

CLAUDE.md has the Cougr rules for Soroban code, no_std, the standards layer, and examples. CONTRIBUTING.md has the full contributor guide. Read the doc for the area you touch before writing code.

Read the full file on GitHub · 42 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.

today First seen · 42 lines · 605 tokens per session scan A f18591b80531

Subscribe to this mod's changes

Cougr AGENTS.md is an instructions file published in the GitHub repository salazarsebas/Cougr (53 stars, last pushed 17d ago), licensed MIT. It adds 605 tokens to every session, about $0.0024 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 2026-11-07.

Commits Git and workflow blockchain-gaming ecs game-engine on-chain-games soroban

Cougr AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Cougr AGENTS.mdsalazarsebas/Cougr	Instructions file	53	17d ago	MIT	A	605	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

Cougr: Instructions file for Codex