What is kiro-for-codex AGENTS.md?

Repository-wide instructions for Kiro for Codex, a coding assistant. It explains which project guidance files take priority, how the assistant should behave, and how it should run commands.

Following steering documents, resolving instruction conflicts, locating project paths, and running command-line work through the repository's required tools.

It reduces conflicting instructions and keeps changes aligned with the repository's product, technical, and structural decisions.

How atman-33/kiro-for-codex configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to atman-33/kiro-for-codex. 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/atman-33/kiro-for-codex/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/atman-33/kiro-for-codex

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/atman-33/kiro-for-codex/agents-md/github.svg)](https://agentmods.dev/instructions/atman-33/kiro-for-codex/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/atman-33/kiro-for-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/atman-33/kiro-for-codex/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/atman-33/kiro-for-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/atman-33/kiro-for-codex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 737 This file is loaded in full into every session.

When invoked 737 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	$0.00737	$0.00737
Opus 5.5	$0.00295	$0.00295
Sonnet 5.5	$0.00147	$0.00147
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash 47fad85e5dce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kiro-for-codex 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Kiro for Codex

This file defines the agent contract and serves as the index to project guidance. It applies repo‑wide unless overridden by a nested AGENTS.md.

Steering Documents

Use Steering as the authoritative source for product, technical, and structural guidance.
Location: .codex/steering/product.md, .codex/steering/tech.md, .codex/steering/structure.md.
Access: Resolve paths via ConfigManager (e.g., ConfigManager.getPath('steering')). Do not hardcode absolute paths.
Mutations: Treat Steering as read‑only; perform changes only via feature flows (Init/Refine/Delete), not ad‑hoc edits.
Usage: When producing outputs, summarize applicable Steering points and cite the specific file/section; do not restate content verbatim.

Decision Precedence

Code-level flags and constraints in "src/constants.ts"
Steering documents under ".codex/steering/*.md"
This AGENTS.md contract (general repository conventions)
Generic assumptions (avoid unless explicitly allowed)

Agent Behavior Contract

Use CodexProvider for CLI operations; build commands with CommandBuilder; execute via ProcessManager. Do not spawn child processes directly.
Respect feature flags and constraints in src/constants.ts and any package.json contributes.* gating.
Logging: Use the shared OutputChannel; log key lifecycle and error paths; avoid noisy logs.
Error handling: Use centralized services (ErrorHandler, RetryService); avoid ad‑hoc try/catch loops.
Performance/UX: Do not block the extension host; for long tasks use split terminals and VS Code progress notifications.
Reference Steering for naming, boundaries, and directory layout instead of restating rules here.

Paths & I/O

Workspace I/O: Prefer VS Code FS APIs (vscode.workspace.fs) for read/write/create.
Path resolution: Use ConfigManager for all .codex/** paths; avoid absolute paths.
Write boundaries: Only write within .codex/**, the workspace, or VS Code storage as allowed by project rules.
Steering: Do not overwrite files under .codex/steering directly; use feature flows.

Read the full file on GitHub · 54 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 · 54 lines · 737 tokens per session scan A 47fad85e5dce

Subscribe to this mod's changes

kiro-for-codex AGENTS.md is an instructions file published in the GitHub repository atman-33/kiro-for-codex (65 stars, last pushed 1y ago), licensed MIT. It adds 737 tokens to every session, about $0.0029 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.

ai-assisted-development codex-cli spec-driven-development vscode-extension

kiro-for-codex AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kiro-for-codex AGENTS.mdatman-33/kiro-for-codex	Instructions file	65	1y ago	MIT	A	737	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

kiro-for-codex: Instructions file for Codex