Borrowing it
Nothing to install: this file belongs to h1902y/zuzuu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/h1902y/zuzuu/main/CLAUDE.mdgit clone --depth 1 https://github.com/h1902y/zuzuuWrote 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/h1902y/zuzuu/claude-md)<a href="https://agentmods.dev/instructions/h1902y/zuzuu/claude-md"><img src="https://agentmods.dev/badge/instructions/h1902y/zuzuu/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 | $0.07860 | $0.07860 |
| Opus 5 | $0.03930 | $0.03930 |
| Sonnet 5 | $0.01572 | $0.01572 |
| Haiku 4.5 | $0.00786 | $0.00786 |
Grade A, and why
zuzuu 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 8d 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 — 143 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 this repository is
A working early-stage build + its canonical design. The host coding-agent (Claude Code / Codex / Gemini CLI / OpenCode / pi) supplies the brain; this project gives it evolving modules — Knowledge (semantic), Memory (episodic), Actions (procedural), Instructions (directive), Guardrails (protective, enforced) — that graduate across versioned generations, grown from the observability trace of real use, human-gated. We wrap, serve, observe, evolve a host we never drive. (Terminology: these five were called faculties until the faculty → module rename — code, CLI, README, and DESIGN now say module; faculty survives only as intentional history — the commands/migrations/ shims, DESIGN.md's terminology notes, and LOG.md's append-only journal entries — not as drift to fix.)
The v2 rebuild is now the product (rungs 1–8 shipped on rebuild/kernel, 2026-06-21). The filesystem-native note / module / project model the redesign specs described is built and the v1 substrate is deleted — ~13k → ~3.6k lines. One coherent stack, filed by concept: src/{notes,use,grow,guardrails,hosts,sessions,cli,serve}. Everything is an envelope (markdown + frontmatter, distinguished by type): a note (one fact, optionally runnable) and a module manifest are the same shape. The four capability verbs — query · act · check · review — are CLI verbs over envelopes, dispatched through one registry (enhance was cut 2026-06-22 — its co-invocation miner was structurally dead; observe is the live proposal producer). The loop is observe → propose → review → evolve (review = the human gate's decision; evolve = write the note + mint a generation + log), every write human-gated (the gate is the moat). Built + verified: the substrate (the envelope parser, the node:sqlite graph index, the capability registry, content-addressed per-module generations), the loop (propose/review), observe (host-agnostic transcript mining → routed proposals, Design B — re-parse, never drive), the CLI veneer (bin/zuzuu.mjs → cli/ → api), session management (session = git branch; worktrees + labels — the safety-critical sessions/ engine, characterization-tested), the live hook (lifecycle + the enforced PreToolUse gate), and host enablement. The published binary runs the whole loop end to end. Check docs/LOG.md for the build journal and docs/learn/ for the educative walk (lessons 02–08 cover the rebuild).
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.
- 8d ago First seen · 143 lines · 7,860 tokens per session scan A c47280a3b88b
zuzuu CLAUDE.md is an instructions file published in the GitHub repository h1902y/zuzuu (1 stars, last pushed 4d ago), licensed MIT. It adds 7,860 tokens to every session, about $0.0393 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.