What is codex-oss-agent-kit AGENTS.md?

A set of repository rules for AI agents and developers working on a TypeScript project. It defines which folders contain business logic, command-line code, shared types, and tests, plus coding and quality requirements.

Use it to decide where new code belongs, enforce strict TypeScript types, follow formatting and lint rules, and run the project's tests.

It prevents code from crossing the wrong architectural boundaries and makes expected checks clear before changes are considered complete.

codex-oss-agent-kit AGENTS.md — Instructions file by thangnqdev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/thangnqdev/codex-oss-agent-kit/agents-md

Clone the repo

git clone --depth 1 https://github.com/thangnqdev/codex-oss-agent-kit

Made for: Codex, OpenCode.

Per session 541 This file is loaded in full into every session.

When invoked 541 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00541	$0.00541
Opus 5	$0.00270	$0.00270
Sonnet 5	$0.00108	$0.00108
Haiku 4.5	$0.00054	$0.00054

Measured 2d ago against content hash b02921bd57dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-oss-agent-kit 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 2d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Instructions for AI Agents & Developers

This repository follows an internal architecture, coding, testing, and security contract for human maintainers and AI coding agents. These rules are repository policy, not an official OpenAI program standard.

1. Architectural Contract & Directory Boundaries

src/core/: Contains pure business logic, analyzers, and OpenAI Codex integrations. Must remain framework-agnostic.
src/cli/: Command-line entry points and interactive subcommands.
src/types/: Shared TypeScript data models, contracts, and interfaces.
tests/: Vitest test specifications matching 1-to-1 with core modules.

Layer Dependency Direction

src/cli/ -> src/core/ -> src/types/

Never import CLI modules inside core or types.

2. Coding & Quality Standards

TypeScript Strict Mode: Zero any types permitted. All functions must declare explicit parameter types and return types. noUncheckedIndexedAccess is enabled; index access must be narrowed before use.
Lint & Format: ESLint (typescript-eslint type-aware rules) and Prettier are enforced. npm run lint and npm run format:check must pass.
Immutability: Prefer readonly arrays/objects for state representations.
Error Handling: Use custom domain exceptions (CodexApiError, ValidationError, SecurityAuditError) rather than bare throw new Error().
Async Safety: Always wrap external network/API operations with timeout, retry, and clean failure handlers. Chunked review calls run with bounded concurrency (mapWithConcurrency), never unbounded fan-out.

3. Testing Contract

Test Suite: Vitest (npm run test).
Coverage Floor: 80% line, statement, branch, and function coverage minimum, enforced per file (perFile: true).
Determinism: Mock external HTTP calls or OpenAI API requests using fakes/stubs in tests.

4. Completion & Quality Gate Criteria

Before submitting any PR or marking work complete:

Read the full file on GitHub · 51 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.

2d ago First seen · 51 lines · 541 tokens per session scan A b02921bd57dd

Subscribe to this mod's changes

codex-oss-agent-kit AGENTS.md is an instructions file published in the GitHub repository thangnqdev/codex-oss-agent-kit (101 stars, last pushed 6d ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 per session on Opus 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.

Code review Planning Testing

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex-oss-agent-kit AGENTS.md