kiro-for-codex-ide AGENTS.md

kiro-for-codex-ide AGENTS.md is an instructions file for Codex, OpenCode from atman-33/kiro-for-codex-ide. It costs 863 tokens per session, scanned A, original, MIT.

Repository instructions for Kiro for Codex IDE, covering its specifications, steering documents, project structure, and rules for agent behavior.

In plain words
What is it for?
Use them when planning changes, creating proposals, or modifying the Kiro for Codex IDE project.
Why use it?
They tell the agent which project documents are authoritative and when it must consult a proposal or specification.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

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/atman-33/kiro-for-codex-ide/agents-md
Clone the repo
git clone --depth 1 https://github.com/atman-33/kiro-for-codex-ide

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.

agentmods badge for kiro-for-codex-ide AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atman-33/kiro-for-codex-ide/agents-md.svg)](https://agentmods.dev/instructions/atman-33/kiro-for-codex-ide/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/atman-33/kiro-for-codex-ide/agents-md"><img src="https://agentmods.dev/badge/instructions/atman-33/kiro-for-codex-ide/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 863 This file is loaded in full into every session.
When invoked 863 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00863 $0.00863
Opus 5 $0.00432 $0.00432
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00086 $0.00086

Measured 6d ago against content hash 06f2c0ffe731, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kiro-for-codex-ide 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 6d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Instructions

These instructions are for AI assistants working in this project.

Always open @/openspec/AGENTS.md when the request:

  • Mentions planning or proposals (words like proposal, spec, change, plan)
  • Introduces new capabilities, breaking changes, architecture shifts, or big performance/security work
  • Sounds ambiguous and you need the authoritative spec before coding

Use @/openspec/AGENTS.md to learn:

  • How to create and apply change proposals
  • Spec format and conventions
  • Project structure and guidelines

Keep this managed block so 'openspec update' can refresh the instructions.

AGENTS Contract

Steering Documents

  • Use .codex/steering/product.md, .codex/steering/tech.md, .codex/steering/structure.md as the authoritative sources for product, technical, and structural rules; summarize them only by reference.
  • Access Steering paths via ConfigManager.getPath("steering"); avoid hardcoding .codex/steering strings outside existing helpers.
  • Treat Steering files as read-only; invoke SteeringManager workflows for any additions, refinements, or deletions.
  • Cite the specific Steering file and (when relevant) section headers in deliverables instead of copying their contents.

Decision Precedence

  1. Steering documents under .codex/steering/*.md.
  2. This AGENTS contract.
  3. Explicit user instructions.
  4. Generic assumptions (use only when none of the above apply).

Agent Behavior Contract

  • Use SpecManager (src/features/spec/spec-manager.ts) and SteeringManager (src/features/steering/steering-manager.ts) for lifecycle operations; do not reimplement their logic.
  • Route prompts through PromptLoader (src/services/prompt-loader.ts) and CodexProvider (src/providers/codex-provider.ts) instead of spawning unmanaged terminals or reading prompt files directly.
  • Respect feature gating and configuration resolved by ConfigManager (src/utils/config-manager.ts); update workspace settings via its APIs rather than manual file edits.
  • Prefer shared utilities in src/utils/* for notifications, chat integration, and configuration; avoid bespoke implementations.
  • Keep logging scoped to the provided output channel (outputChannel from src/extension.ts) and avoid excessive noise.

Read the full file on GitHub · 64 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.

  1. 6d ago First seen · 64 lines · 863 tokens per session scan A 06f2c0ffe731

Subscribe to this mod's changes

kiro-for-codex-ide AGENTS.md is an instructions file published in the GitHub repository atman-33/kiro-for-codex-ide (16 stars, last pushed 10mo ago), licensed MIT. It adds 863 tokens to every session, about $0.0043 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.

Related

Other instructions, from other repositories

kiro-for-codex AGENTS.md

Instructions for atman-33/kiro-for-codex, covering agents.md — kiro for codex, steering documents, decision precedence, agent behavior contract and paths & i/o.

atman-33/kiro-for-codex · 737 tokens

speckit-companion CLAUDE.md

Claude Code instructions for alfredoperez/speckit-companion, covering claude.md, where things are documented, gotchas, two extensions, two sets of docs and /releases/latest resolves across both tag namespaces.

alfredoperez/speckit-companion · 1,429 tokens

speckit-companion copilot-instructions.md

Copilot instructions for alfredoperez/speckit-companion: For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan: specs/120-reorder-sidebar-icons/plan.md.

alfredoperez/speckit-companion · 50 tokens

speckit-companion AGENTS.md

AGENTS.md instructions for alfredoperez/speckit-companion: For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan: specs/108-clarify-provider-labels/plan.md.

alfredoperez/speckit-companion · 52 tokens

pilot-shell AGENTS.md

AGENTS.md instructions for maxritter/pilot-shell, covering pilot shell repository instructions, project, commands, repository rules and cross-agent assets.

maxritter/pilot-shell · 706 tokens

pilot-shell CLAUDE.md

Claude Code instructions for maxritter/pilot-shell, a project described as: Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

maxritter/pilot-shell · 5 tokens