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.
npx agentmods add instructions/atman-33/kiro-for-codex-ide/agents-mdgit clone --depth 1 https://github.com/atman-33/kiro-for-codex-ideWrote 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.
[](https://agentmods.dev/instructions/atman-33/kiro-for-codex-ide/agents-md)<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>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 | $0.00863 | $0.00863 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
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.
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.mdas the authoritative sources for product, technical, and structural rules; summarize them only by reference. - Access Steering paths via
ConfigManager.getPath("steering"); avoid hardcoding.codex/steeringstrings outside existing helpers. - Treat Steering files as read-only; invoke
SteeringManagerworkflows 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
- Steering documents under
.codex/steering/*.md. - This AGENTS contract.
- Explicit user instructions.
- Generic assumptions (use only when none of the above apply).
Agent Behavior Contract
- Use
SpecManager(src/features/spec/spec-manager.ts) andSteeringManager(src/features/steering/steering-manager.ts) for lifecycle operations; do not reimplement their logic. - Route prompts through
PromptLoader(src/services/prompt-loader.ts) andCodexProvider(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 (
outputChannelfromsrc/extension.ts) and avoid excessive noise.
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.
- 6d ago First seen · 64 lines · 863 tokens per session scan A 06f2c0ffe731
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.
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.
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.
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.
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.
pilot-shell AGENTS.md
AGENTS.md instructions for maxritter/pilot-shell, covering pilot shell repository instructions, project, commands, repository rules and cross-agent assets.
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.