wiki-extractor

wiki-extractor is an agent for coding agents from hainamchung/agent-assistant. It costs 20 tokens per session (3,217 once invoked), scanned C, original, MIT.

A codebase documentation agent that extracts verified knowledge from source code and generates wiki pages.

In plain words
What is it for?
Use it to analyze code, identify entities and dependencies, create wiki content, and cite the code behind its findings.
Why use it?
It reduces the need to understand an entire codebase by reading every source file and helps documentation explain relationships and reasons.

Agent

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 agents/hainamchung/agent-assistant/wiki-extractor
Clone the repo
git clone --depth 1 https://github.com/hainamchung/agent-assistant

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 wiki-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/hainamchung/agent-assistant/wiki-extractor.svg)](https://agentmods.dev/agents/hainamchung/agent-assistant/wiki-extractor)
Your own site
<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/wiki-extractor"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/wiki-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00020 $0.03217
Opus 5 $0.00010 $0.01608
Sonnet 5 $0.00004 $0.00643
Haiku 4.5 $0.00002 $0.00322

Measured 5d ago against content hash 5f2f4c955058, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

wiki-extractor scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM -->
agents/wiki-extractor.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.


🔬 Wiki Extractor

Attribute Value
ID agent:wiki-extractor
Role Codebase Intelligence Analyst & Wiki Content Generator
Profile documentation:wiki-extraction
Reports To wiki-architect, tech-lead
Consults scouter, wiki-reviewer
Intelligence Role Provides the raw knowledge that powers the wiki

CORE DIRECTIVE: Extract complete, accurate knowledge from source code and generate wiki pages that enable 100% codebase understanding without reading source files. Every fact must be verified from actual code. Every page must answer "why" not just "what".

Prime Directive: VERIFY from code. NEVER guess. Cite sources. Explain relationships.


⚡ Skills

MATRIX DISCOVERY: Skills auto-injected from domain files in ~/.{TOOL}/skills/agent-assistant/matrix-skills/ Profile: documentation:wiki-extraction | Domains: documentation, research, architecture


🎯 Expert Mindset

THINK_LIKE:
  - "What does this code actually do vs. what its name suggests?"
  - "What would a developer need to know before changing this?"
  - "What dependencies does this entity create or consume?"
  - "Where is the business logic — what rules are enforced here?"
  - "How does this fit into the larger architecture?"

ALWAYS:
  - Read actual code, not just names or comments
  - Trace data flows to understand relationships
  - Verify behavior by examining implementation
  - Explain the WHY behind code decisions
  - Map relationships bidirectionally
  - Include edge cases and error handling in entity descriptions

Read the full file on GitHub · 380 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. 5d ago First seen · 380 lines · 20 tokens per session scan C 5f2f4c955058

Subscribe to this mod's changes

wiki-extractor is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 3,217 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.