kition: Instructions file for Codex

AGENTS.md

kition AGENTS.md is an instructions file for Codex, OpenCode from KitionAI/kition. It costs 2,587 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for KitionAI/Kition, a software workspace. It defines rules for privacy, portable file paths, interface design, and checking that work is complete.

In plain words
What is it for?
Use it when working in the Kition workspace to follow its required privacy and design rules and to complete the required end-to-end check before declaring a task finished.
Why use it?
It gives coding agents consistent rules to follow while changing the project. It reduces privacy mistakes, platform-specific paths, and unfinished changes that were not tested.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is KitionAI/kition's own configuration. It tells Codex and OpenCode how to work on kition itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kition configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/alice/....

Reuse

Borrowing it

Nothing to install: this file belongs to KitionAI/kition. 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/KitionAI/kition/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/KitionAI/kition

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 kition AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kitionai/kition/agents-md/github.svg)](https://agentmods.dev/instructions/kitionai/kition/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kitionai/kition/agents-md"><img src="https://agentmods.dev/badge/instructions/kitionai/kition/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.

agentmods 80×15 button for kition AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kitionai/kition/agents-md"><img src="https://agentmods.dev/badge/instructions/kitionai/kition/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,587 This file is loaded in full into every session.
When invoked 2,587 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02587 $0.02587
Opus 5.5 $0.01035 $0.01035
Sonnet 5.5 $0.00517 $0.00517
Haiku 4.5 $0.00259 $0.00259

Measured today against content hash 8e59c484d2ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kition 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 today.

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 · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kition Workspace Rules

Quality rules (read first)

  • Tests are the spec. Read QUALITY.md and the feature catalogue (features.yaml) before changing behaviour. When code and a case disagree, the case wins unless the owner approves changing the case.
  • Before you finish any task, run pnpm -s typecheck && pnpm -s lint. If it fails, the task is not done. Claude Code runs it for you through the Stop hook; agents without hooks (Codex) run it by hand and report the real exit code.
  • Never edit expected results to make a test pass: files under cases/**/expected/, paths listed under protected in features.yaml, and the expected, tolerance, reference, input and steps of an existing case.yaml. If you believe an expected result is wrong, stop and explain why in the task's findings; only the owner approves expected-result changes.
  • Never weaken a test to make it pass: no deleted or loosened assertions, no added #[ignore], .skip, .only or .todo, no raised tolerances. kition-sdk's tools/check-expected.mjs lists every such change for the owner.
  • Every bug fix starts with a failing case under cases/regressions/issue-<n>/, then the fix.
  • Every new feature adds an entry to features.yaml and at least one golden case.
  • Put the task card id and the case ids in the commit message.
  • Stage only your own files: git add them by name; never git commit -a or git add -A. Other sessions may have uncommitted work in the same checkout.
  • Never touch kition-slide or any worktree of it: do not change, build, or commit there.
  • No compatibility layers: no aliases, old names, old file suffixes, migrations, or readers for old formats. Delete a replaced path in the same change.

The product name is Kition (kition.ai). Never introduce any historical product name, slug, package name, module name, app ID, environment prefix, database name, or dotfile directory into code or documentation. The canonical identity contract lives in openspec/specs/branding/.

Read the full file on GitHub · 191 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. today Changed · +26 lines · +462 tokens per session 8e59c484d2ee
  2. 3d ago Changed · +1 tokens per session 5dd6b111908f
  3. 4d ago Changed · +2 lines · +44 tokens per session 76117dfab255
  4. 5d ago Changed · +3 lines · +58 tokens per session 87049ecef1f4
  5. 6d ago Changed · +6 lines · +97 tokens per session 4588e4ca0b0a
  6. 7d ago Changed · +2 lines · +51 tokens per session d5552b6e5922
  7. 9d ago Changed · -2 tokens per session eaf6862d13c7
  8. 11d ago Changed · +2 tokens per session b14ad5683e07
  9. 14d ago Changed · +4 lines · +66 tokens per session 855ae05dc114
  10. 15d ago First seen · 148 lines · 1,808 tokens per session scan A 029e34720eee

Subscribe to this mod's changes

kition AGENTS.md is an instructions file published in the GitHub repository KitionAI/kition (549 stars, last pushed today), licensed Apache-2.0. It adds 2,587 tokens to every session, about $0.0103 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

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 · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens