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/tpierrain/kenjaku/claude-mdgit clone --depth 1 https://github.com/tpierrain/kenjakuWrote 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/tpierrain/kenjaku/claude-md)<a href="https://agentmods.dev/instructions/tpierrain/kenjaku/claude-md"><img src="https://agentmods.dev/badge/instructions/tpierrain/kenjaku/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 | $0.05247 | $0.05247 |
| Opus 5 | $0.02624 | $0.02624 |
| Sonnet 5 | $0.01049 | $0.01049 |
| Haiku 4.5 | $0.00525 | $0.00525 |
Grade A, and why
kenjaku 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 5d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 Kenjaku — your second brain (self-install notice, for Claude)
This folder is the LAUNCHER (the generator), not a second brain. This file is a bootstrap stub: the installer creates a separate brain folder and drops the real constitution there (a personalized
CLAUDE.md). The launcher itself is never modified: it stays read-only and reusable (a single launcher can generate several brains).For Claude. If the user asks you to create / install their second brain (or asks the second brain a question while this bootstrap stub is still here), follow the steps below EXACTLY. You can drive the whole machinery yourself: the installer runs in non-interactive mode (
--non-interactive) — so you do NOT need the user to launch it at the keyboard. You gather the answers in chat, then you call a single command.
🛠️ Maintainer note (only if you are DEVELOPING the launcher itself — not installing a brain): also follow
maintainers/CONVENTIONS.md. It carries the repo's durable rules (checkboxes on every plan step, one canonical plan = the repo's, artifacts in English, TDD baby-steps + green-only commits, ADRScope:field, plan-done = archived, and a marketing-surface re-read at every release) so they travel with the clone instead of living only on one machine. This note is part of the installer stub, so it is overwritten at install and never reaches a generated brain.
Step 1 — Get the launcher (normal clone)
(Often already done if you are reading this file from inside the folder.) If you start from a URL:
git clone --depth 1 <REPO_URL> <launcher-folder>
cd <launcher-folder>
The launcher is reusable and never touched by the install: the installer creates a fresh
brain folder elsewhere, copies the files into it, then runs git init inside it → no link
back to the launcher, by construction (no inherited remote to remove). The brain's auto-commit hook
pushes nothing until the user has wired up THEIR own remote repository (push is opt-in).
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.
- 5d ago First seen · 267 lines · 5,247 tokens per session scan A 2e019a1191f4
kenjaku CLAUDE.md is an instructions file published in the GitHub repository tpierrain/kenjaku (80 stars, last pushed today), licensed Apache-2.0. It adds 5,247 tokens to every session, about $0.0262 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
llm-brain CLAUDE.md
Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.
VLM-wiki AGENTS.md
Instructions for VeniVeci/VLM-wiki, covering vlm wiki agent, core philosophy, architecture, special files and model configuration.
cmds-llm-wiki AGENTS.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.
cmds-llm-wiki CLAUDE.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
lobu AGENTS.md
AGENTS.md instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.