wikifier CLAUDE.md

wikifier CLAUDE.md is an instructions file for coding agents from IronAdamant/wikifier. It costs 2,270 tokens per session, scanned A, original, MIT.

A project-specific instruction file for Wikifier, a tool that gives coding agents a searchable map of a codebase. It describes the repository's workflow, constraints, and required agent tools.

In plain words
What is it for?
It helps agents inspect the codebase, prepare edits, record changes, and follow the project's own development protocol.
Why use it?
It tells an agent how to work safely and consistently in this repository instead of relying on general assumptions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ironadamant/wikifier/claude-md
Clone the repo
git clone --depth 1 https://github.com/IronAdamant/wikifier

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 wikifier CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ironadamant/wikifier/claude-md.svg)](https://agentmods.dev/instructions/ironadamant/wikifier/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ironadamant/wikifier/claude-md"><img src="https://agentmods.dev/badge/instructions/ironadamant/wikifier/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,270 This file is loaded in full into every session.
When invoked 2,270 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02270 $0.02270
Opus 5 $0.01135 $0.01135
Sonnet 5 $0.00454 $0.00454
Haiku 4.5 $0.00227 $0.00227

Measured today against content hash aa4eed92d69d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

wikifier 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.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 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 Is

Wikifier is a zero-dependency, agent-to-agent codebase wiki: it gives AI agents a token-efficient, queryable map of a codebase (health matrix, dependency graph, per-file wiki summaries) so they can look things up instead of re-reading full sources. The human layer (index.html dashboard) is strictly secondary — a read-only viewer of the same artifacts. It is deliberately NOT a general human documentation tool.

This repo dogfoods itself. Wikifier runs on its own source, and you are expected to follow its agent protocol when working here (see below). The authoritative agent contract is skills/run.md (Agent Protocol v0.6 — package 4.6.x) — read it before substantive work.

USE WIKIFIER FIRST (non-negotiable in this repo, preferred on any managed target): At session start call session_bootstrap (MCP or python -m wikifier session-bootstrap). Prefer Core daily tools (list_core_tools): bootstrap, check_changes, prepare_edit, suggest_next_actions (json actions[]), record_change, mark_green. Look up via map/wiki/deps before re-reading full sources. Selective work only (🔴 / actionable 🟡). Never skip record_change after edits.

Hard Constraints

  • NON-NEGOTIABLE: effectively zero-dependency. The core must run on pure Python stdlib (>=3.8) + POSIX shell alone — pyproject.toml declares dependencies = [] and that stays. The reason is architectural, not stylistic: anyone forking this project must be free to bring their own third-party libraries on top of a dependency-free base. Therefore: never add a runtime dependency, never couple core logic to an optional extra (the mcp extra must remain strictly optional and isolated to wikifier/mcp/), and never make core behavior degrade when nothing beyond the stdlib is installed.
  • library.md, file_health.md, pending_updates.md are generated/managed artifacts. Never hand-edit library.md (overwritten by update-maps); mutate health/pending only through the official commands (they hold locks).
  • Human-layer separation: only index.html is deployed to target projects on init. diagnostics.html is maintainer-only and stays in this repo.
  • Agent-to-agent scope only — do not grow features toward general human docs or IDE use.

Read the full file on GitHub · 88 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. today First seen · 88 lines · 2,270 tokens per session scan A aa4eed92d69d

Subscribe to this mod's changes

wikifier CLAUDE.md is an instructions file published in the GitHub repository IronAdamant/wikifier (13 stars, last pushed yesterday), licensed MIT. It adds 2,270 tokens to every session, about $0.0113 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 2026-09-04.

Related

Other instructions, from other repositories

abap_wiki AGENTS.md

AGENTS.md instructions for Gixsy95/abap_wiki, covering agents.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.

Gixsy95/abap_wiki · 3,283 tokens

jdocmunch-mcp CLAUDE.md

Claude Code instructions for jgravelle/jdocmunch-mcp, covering jdocmunch-mcp, v1.139.1 — a rate written for a date that never arrived, standing operational notes (jdoc-specific), standing lessons (suite-wide) and release: the two steps that are only written down here.

jgravelle/jdocmunch-mcp · 17,293 tokens

DocGraph AGENTS.md

Instructions for Detective-XH/DocGraph, covering agents.md — docgraph fit guide for llm agents, the fit decision, decisive signals — any one means: use docgraph, supporting signals — useful when several hold together and anti-signals — prefer your own grep/read.

Detective-XH/DocGraph · 1,698 tokens

abap_wiki CLAUDE.md

Claude Code instructions for Gixsy95/abap_wiki, covering claude.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.

Gixsy95/abap_wiki · 3,281 tokens

agent-wiki AGENTS.md

Instructions for xccElephant/agent-wiki, covering llm wiki agent guide, directory roles, core rules, claim types and ingest workflow.

xccElephant/agent-wiki · 739 tokens

negentropy-perceives AGENTS.md

Instructions for ThreeFish-AI/negentropy-perceives, covering agents.md, collaboration protocol (协作协议), project positioning (项目定位), engineering code of conduct (工程行为准则) and 道 (mindset - 认知心法).

ThreeFish-AI/negentropy-perceives · 2,296 tokens