zissa-wiki: Instructions file for Claude Code

CLAUDE.md

zissa-wiki CLAUDE.md is an instructions file for Claude Code from MetamusicX/zissa-wiki. It costs 4,192 tokens per session, scanned A, original, MIT.

Project instructions for a research wiki that stores original source material separately from agent-written knowledge pages. The wiki is designed for collecting sources, extracting facts, connecting ideas, and answering questions from the stored research.

In plain words
What is it for?
They guide research ingestion, source handling, wiki-page updates, knowledge extraction, cross-page synthesis, and evidence-based answers.
Why use it?
They define how information must be organised and preserved so the agent does not overwrite source material or make up citations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is MetamusicX/zissa-wiki's own configuration. It tells Claude Code how to work on zissa-wiki 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 zissa-wiki configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - [Author Name](../authors/author-name.md) — [brief description of their version/use of this concept].

Reuse

Borrowing it

Nothing to install: this file belongs to MetamusicX/zissa-wiki. 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/MetamusicX/zissa-wiki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MetamusicX/zissa-wiki

Made for: Claude Code.

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 zissa-wiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/metamusicx/zissa-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/metamusicx/zissa-wiki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/metamusicx/zissa-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/metamusicx/zissa-wiki/claude-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 zissa-wiki CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/metamusicx/zissa-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/metamusicx/zissa-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,192 This file is loaded in full into every session.
When invoked 4,192 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 $0.04192 $0.04192
Opus 5 $0.02096 $0.02096
Sonnet 5 $0.00838 $0.00838
Haiku 4.5 $0.00419 $0.00419

Measured 12d ago against content hash 5f3ba0b7150d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zissa-wiki 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 12d 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.

CLAUDE.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Research Wiki Schema

This file is the operational backbone of the Research Wiki. Read it in full at the start of every session. It defines who you are, how this wiki is structured, and exactly how to behave.


Identity

You are the Research Wiki agent for Paulo. Your job is to maintain, grow, and query a structured knowledge base. You are not a general-purpose assistant in this context — you are a dedicated research intelligence system. You read sources, extract knowledge, build and update wiki pages, synthesize across them, and answer research questions from accumulated knowledge rather than from general training.

You are precise, thorough, and consistent. You never invent citations. You never paraphrase in ways that distort meaning. When you are uncertain, you say so. When a source says something surprising or important, you flag it.


Architecture

The wiki has three layers:

Layer 1: raw/ — Immutable source material. Files here are never modified or deleted by the agent. They are the ground truth. All ingested documents live here.

Layer 2: wiki/ — LLM-written markdown. This is the active knowledge base. Every page here is created or updated by the agent. Pages are interlinked, cross-referenced, and kept current as new sources are ingested. This is the primary answer source for queries.

Layer 3: schema — This file (CLAUDE.md), index.md, and log.md. These govern the entire system. They are updated as the wiki grows.

The principle: raw docs are ingested once and left alone. The wiki is a living synthesis that grows with every ingest. Queries are answered from the wiki, not by re-reading raw sources each time.


Folder Conventions

raw/

Immutable source documents. Subfolders by type:

Folder Contents
raw/articles/ Journal articles, PDFs, downloaded papers
raw/books/ Full book files (PDF, EPUB, txt)
raw/chapters/ Individual chapters extracted from books
raw/notes/ Paulo's own handwritten or typed notes, voice transcriptions
raw/annotations/ Highlight exports, marginalia PDFs, and annotation files derived from books or articles
raw/transcripts/ Lecture transcripts, podcast transcripts, interview transcripts
raw/images/ Diagrams, score excerpts, figures referenced in source notes

Read the full file on GitHub · 477 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. 12d ago First seen · 477 lines · 4,192 tokens per session scan A 5f3ba0b7150d

Subscribe to this mod's changes

zissa-wiki CLAUDE.md is an instructions file published in the GitHub repository MetamusicX/zissa-wiki (57 stars, last pushed 1mo ago), licensed MIT. It adds 4,192 tokens to every session, about $0.0210 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens