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/bokiko/kyzn/claude-mdgit clone --depth 1 https://github.com/bokiko/KyZNWrote 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/bokiko/kyzn/claude-md)<a href="https://agentmods.dev/instructions/bokiko/kyzn/claude-md"><img src="https://agentmods.dev/badge/instructions/bokiko/kyzn/claude-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 | $0.02105 | $0.02105 |
| Opus 5 | $0.01052 | $0.01052 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
KyZN CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is KyZN
KyZN (from "kaizen") is a pure-Bash CLI that autonomously improves code quality. It runs real language tools to produce a health score, invokes Claude Code to make improvements, gates changes behind build/test verification and score regression checks, then opens a GitHub PR with before/after comparison. Supports Node.js, Python, Rust, Go, C# / .NET, and Java / JVM.
Prerequisites
Bash 4.3+, git, gh (GitHub CLI), claude (Anthropic CLI), jq, yq, and either Perl or Python 3 for portable safety controllers. Language-specific tools are optional (eslint/tsc, ruff/mypy, cargo, go vet, etc.).
Commands
# Run tests
kyzn selftest # Quick self-test suite
kyzn selftest --full # Include stress tests
bash tests/selftest.sh # Direct test runner
# Lint (matches CI)
shellcheck -S warning kyzn lib/*.sh measurers/*.sh tests/selftest.sh tests/toolchain/run-matrix.sh
# Usage
kyzn doctor # Check prerequisites
kyzn doctor --install --allow-unsafe-host-execution # Opt in to dependency install on this host
kyzn init # Interactive setup → .kyzn/config.yaml
kyzn measure # Static measurements (no project commands)
kyzn measure --allow-unsafe-host-execution # Include package/build-tool measurements
kyzn fix --allow-unsafe-host-execution # Deep analysis + auto-fix → PR (recommended)
kyzn fix --auto --allow-unsafe-host-execution # Non-interactive; manual PR review required
kyzn analyze # 4 Opus specialists + consensus report (no changes)
kyzn quick --allow-unsafe-host-execution # Quick single-pass improvement
kyzn quick --auto --allow-unsafe-host-execution # Non-interactive; manual PR review required
Architecture
Entry point and library loading
kyzn is the entry point — it routes subcommands and lazy-loads only the lib/*.sh modules needed. quick loads 8 libs; measure loads 2; doctor loads none (all inline).
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.
- today Changed 95d44aa21a1b
- 5d ago First seen · 146 lines · 2,105 tokens per session scan A a551e2b3046e
KyZN CLAUDE.md is an instructions file published in the GitHub repository bokiko/KyZN (3 stars, last pushed 2d ago), licensed MIT. It adds 2,105 tokens to every session, about $0.0105 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 2026-08-31.
Other instructions, from other repositories
rigour AGENTS.md
Instructions for rigour-labs/rigour, covering agents.md - universal ai agent instructions, setup, quality gates, 🛡️ rigour: mandatory engineering governance protocol and 🚦 the mandatory governance loop.
rigour CLAUDE.md
Instructions for rigour-labs/rigour, covering claude.md - project instructions for claude code, project overview, commands, verify quality gates and get fix packet for failures.
mcp-devtools-server CLAUDE.md
Claude Code instructions for rshade/mcp-devtools-server, covering claude.md, project overview, specialized agents available, implementation agents and issue management.
mcp-devtools-server AGENTS.md
AGENTS.md instructions for rshade/mcp-devtools-server, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
sheriff-mcp CLAUDE.md
Claude Code instructions for ryansmith4/sheriff-mcp, covering sheriff-mcp development guide, project overview, versioning, version source and release process.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.