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 agents/hainamchung/agent-assistant/wiki-extractorgit clone --depth 1 https://github.com/hainamchung/agent-assistantWrote 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/agents/hainamchung/agent-assistant/wiki-extractor)<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>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 | $0.00020 | $0.03217 |
| Opus 5 | $0.00010 | $0.01608 |
| Sonnet 5 | $0.00004 | $0.00643 |
| Haiku 4.5 | $0.00002 | $0.00322 |
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 --> 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
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 · 380 lines · 20 tokens per session scan C 5f2f4c955058
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.