What is gh-infra AGENTS.md?

Repository instructions for gh-infra, a tool whose workflow plans changes and then applies them to GitHub repositories. They define design rules, dependency handling, validation, and how planned changes must match applied changes.

Use them when changing gh-infra's plans, apply workflow, repository settings, dependency rules, validation, or user-facing principles documentation.

They help an agent avoid applying unplanned changes or silently ignoring unreadable settings. They also preserve the required order and keep related documentation consistent.

How babarot/gh-infra configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to babarot/gh-infra. 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/babarot/gh-infra/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/babarot/gh-infra

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/babarot/gh-infra/agents-md/github.svg)](https://agentmods.dev/instructions/babarot/gh-infra/agents-md)

Your own site

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

Per session 1,374 This file is loaded in full into every session.

When invoked 1,374 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	$0.01374	$0.01374
Opus 5.5	$0.00550	$0.00550
Sonnet 5.5	$0.00275	$0.00275
Haiku 4.5	$0.00137	$0.00137

Measured 25d ago against content hash a80a03742178, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gh-infra 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 25d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Design Principles

plan is the only review in the workflow gh-infra is built for (plan on a pull request, apply on merge), so every change must keep these three rules. The user-facing version is docs/src/content/docs/introduction/principles.md; keep both in sync.

apply does what plan shows. Every change apply makes is in the plan, and nothing else. What GitHub would reject is caught by validate or plan (for example in repository.ValidateDependencies), not found at apply; a setting GitHub silently does not save is caught after the PATCH (verifyPatchResponse) and reported as failed. A setting or file that cannot be read is reported and its repository left out, never compared as absent or at its default. When order matters (create before FileSets, archive last), apply keeps it and the plan lists changes in that order. apply does not read state back and re-plan. A via: pull_request FileSet for a repository with no commits (or one the same apply creates) is planned as a push (fileset.PushToEmpty), and apply delivers each repository as its plan says.
What a manifest leaves out is left alone. A field not in the manifest is not compared and not sent. Collections are additive; labels, rulesets and branch protection delete undeclared entries only with reconcile: authoritative and the collection present. Secrets, variables and milestones never delete. For settings the API replaces as a whole (branch protection, rulesets), apply reads the current object and sends it back with only the manifest's fields changed, including fields gh-infra does not model.
After apply, plan shows no changes. One apply converges. Anything a run cannot apply is said in the plan (for a new repository: repository.CreateNotes), never left for a later surprise. A via: pull_request FileSet keeps showing its changes until the pull request is merged, by design. gh-infra does not change an already archived repository except to unarchive it, as a rule of its own (some GitHub APIs still accept writes there; do not rely on them): such changes fail that repository at plan (archivedChangesError), and the fake GitHub refuses every write to it. FileSets for it are not caught yet.

Read the full file on GitHub · 55 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.

25d ago First seen · 55 lines · 1,374 tokens per session scan A a80a03742178

Subscribe to this mod's changes

gh-infra AGENTS.md is an instructions file published in the GitHub repository babarot/gh-infra (140 stars, last pushed 3d ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0055 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 2026-10-13.

DevOps and cloud Git and workflow cli gh-extension github go

gh-infra AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gh-infra AGENTS.mdbabarot/gh-infra	Instructions file	140	3d ago	MIT	A	1,374	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

gh-infra: Instructions file for Codex