What is codai AGENTS.md?

Repository instructions for keeping documentation aligned with code changes. They describe where to update guides, release notes, API comments, navigation, and other project documentation.

Updating README files, documentation pages, changelogs, API comments, navigation entries, and checking the documentation site.

They reduce the chance that a code change ships with outdated instructions or missing documentation.

How meysamhadeli/codai configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to meysamhadeli/codai. 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/meysamhadeli/codai/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/meysamhadeli/codai

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/meysamhadeli/codai/agents-md/github.svg)](https://agentmods.dev/instructions/meysamhadeli/codai/agents-md)

Your own site

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

Per session 1,011 This file is loaded in full into every session.

When invoked 1,011 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	$0.01011	$0.01011
Opus 5.5	$0.00404	$0.00404
Sonnet 5.5	$0.00202	$0.00202
Haiku 4.5	$0.00101	$0.00101

Measured 14d ago against content hash 2095e6e25cc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codai 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 14d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for anyone — human or AI — changing this repository.

Documentation ships with the code

A change is not done until the docs that describe it are updated in the same commit.

Changed	Update
Flag, default, exit code, config key	README.md · matching docs/ page · `CHANGELOG.md`
User-visible behaviour or limitation	`CHANGELOG.md` under `## [Unreleased]`
New capability, provider, integration, package	README.md tables · docs/ · `CHANGELOG.md`
Public API surface	XML doc comments · docs/ · `CHANGELOG.md`
Layout or package name	README.md index · `CONTRIBUTION.md`

README.md is a short landing page: pitch, install, feature summary, links to published documentation. Detail goes in docs/, never in the README.
docs/ is the Nextra documentation site. Pages live in docs/content/ as .mdx files with title and description frontmatter. Co-located _meta.js files declare navigation. npm run dev in docs/ previews it at http://localhost:3000/codai/.
Register each new page in its directory's _meta.js or node docs/check.mjs fails. Use native Nextra MDX components and root-relative internal routes; Next.js adds the /codai base path automatically. Public asset URLs must include that prefix.
npm run build exports static HTML to docs/out and builds Pagefind search. docs.yml validates pull requests and deploys pushes to main to GitHub Pages. No hosted documentation account is required.
The public URL is https://meysamhadeli.github.io/codai. Its base path, URL and branding live in docs/site.config.mjs. If hosting changes, update that configuration, README links and Pages settings together. Deployment setup is documented in CONTRIBUTION.md.
Links in README.md point at published docs pages, not local file paths.
CHANGELOG.md entries are user-facing, past tense, under Added / Changed / Fixed / Removed.
Never document behaviour the code does not implement. Docs and code disagreeing is a bug in one of them — fix both.

Read the full file on GitHub · 75 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.

14d ago First seen · 75 lines · 1,011 tokens per session scan A 2095e6e25cc6

Subscribe to this mod's changes

codai AGENTS.md is an instructions file published in the GitHub repository meysamhadeli/codai (373 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,011 tokens to every session, about $0.0040 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 2026-10-24.

Writing and docs chatgpt claude gpt-4 gpt-4o ollama openai

codai AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codai AGENTS.mdmeysamhadeli/codai	Instructions file	373	7d ago	Apache-2.0	A	1,011	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

codai: Instructions file for Codex