What is AgentKaizen AGENTS.md?

Repository instructions for AgentKaizen, a project that measures and improves the behaviour of command-line AI agents. AGENTS.md is a file of rules that guides an agent working in a code repository.

Use it when contributing to AgentKaizen, including running local evaluations, managing traces, testing instruction changes, or configuring optional Weights & Biases tracing.

It tells contributors which environment settings, commands, steering files, and architecture rules apply when developing the repository.

How TheIllusionOfLife/AgentKaizen configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to TheIllusionOfLife/AgentKaizen. 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/TheIllusionOfLife/AgentKaizen/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/TheIllusionOfLife/AgentKaizen

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/theillusionoflife/agentkaizen/agents-md/github.svg)](https://agentmods.dev/instructions/theillusionoflife/agentkaizen/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/theillusionoflife/agentkaizen/agents-md"><img src="https://agentmods.dev/badge/instructions/theillusionoflife/agentkaizen/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/theillusionoflife/agentkaizen/agents-md"><img src="https://agentmods.dev/badge/instructions/theillusionoflife/agentkaizen/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,824 This file is loaded in full into every session.

When invoked 1,824 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	$0.01824	$0.01824
Opus 5.5	$0.00730	$0.00730
Sonnet 5.5	$0.00365	$0.00365
Haiku 4.5	$0.00182	$0.00182

Measured 2mo ago against content hash a4b225453d0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AgentKaizen 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Note for skill users: If you installed this skill via npx skills add TheIllusionOfLife/optimize-coding-agent-skill, the commands in this file are for developing the AgentKaizen repository itself, not for using the skill. Skill users invoke the skill directly in their agent session — no uv or git clone needed.

Purpose

This repository exists to improve CLI-based AI agent behavior with measurable feedback loops. The main product question is not just "can Codex solve a task?" but "which steering surface changed the behavior, and did it help enough to keep?"

Important steering surfaces in this repo include:

AGENTS.md
README.md
eval cases and variants
external skill documents
Codex CLI configuration and profiles

Required Environment

All workflows work without W&B. When Weave is not installed or unconfigured, AgentKaizen runs in local-only mode (traces to ~/.agentkaizen/traces.jsonl, local evaluation, regex-based PII redaction).

For W&B Weave integration (remote tracing and dashboards), set:

WANDB_API_KEY
WANDB_PROJECT

WANDB_ENTITY is also needed for Weave, but it may come from WANDB_ENTITY, .env.local, or the logged-in W&B account if not passed explicitly.

Do not hardcode personal W&B entity or project values in code, docs, examples, or tests.

Useful optional environment variables:

WANDB_BASE_URL for custom or self-hosted W&B deployments
WEAVE_PARALLELISM for tuning eval concurrency
WEAVE_PRINT_CALL_LINK=false for CI or other non-interactive runs
WEAVE_LOG_LEVEL when debugging Weave integration behavior
WEAVE_DISABLED=true for local runs where tracing should be bypassed

Commands You Should Use (Repo Development)

These commands are for developing the AgentKaizen repository. Skill users do not need to run any of these.

Use uv for all Python workflows.

Common commands:

uv sync --group dev
uv run agentkaizen run --prompt "Say only: ok"
uv run agentkaizen run --agent claude-code --prompt "Say only: ok"
uv run agentkaizen session sync --once
uv run agentkaizen session sync --agent claude-code --once
uv run agentkaizen session score --trace-file path/to/interactive-trace.json
uv run agentkaizen eval casegen --limit 20 --output evals/cases.generated.jsonl
uv run agentkaizen eval --cases evals/cases --variant-file evals/variants/<file>.json
uv run --group dev pytest
uv run --group dev ruff check .
uv run --group dev ruff format --check .

Read the full file on GitHub · 123 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 · 123 lines · 1,824 tokens per session scan A a4b225453d0b

Subscribe to this mod's changes

AgentKaizen AGENTS.md is an instructions file published in the GitHub repository TheIllusionOfLife/AgentKaizen (2 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,824 tokens to every session, about $0.0073 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 2026-08-31.

AgentKaizen AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AgentKaizen AGENTS.mdTheIllusionOfLife/AgentKaizen	Instructions file	2	8mo ago	Apache-2.0	A	1,824	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AgentKaizen: Instructions file for Codex