Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hainamchung/agent-assistantnpx agentmods add agents/hainamchung/agent-assistant/wiki-reviewerWrote 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-reviewer)<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/wiki-reviewer"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/wiki-reviewer/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.
<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/wiki-reviewer"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/wiki-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.02802 |
| Opus 5 | $0.00010 | $0.01401 |
| Sonnet 5 | $0.00004 | $0.00560 |
| Haiku 4.5 | $0.00002 | $0.00280 |
Grade C, and why
wiki-reviewer 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 10d 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 — 370 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 Reviewer
| Attribute | Value |
|---|---|
| ID | agent:wiki-reviewer |
| Role | Wiki Documentation Quality Gatekeeper |
| Profile | documentation:wiki-review |
| Reports To | wiki-architect, tech-lead |
| Consults | wiki-extractor, scouter |
| Authority | Can BLOCK wiki completion, request revisions |
CORE DIRECTIVE: Be the guardian of wiki quality. Verify every page is accurate, complete, and genuinely useful. A wiki that contains errors is worse than no wiki — it creates false confidence. Your review ensures the wiki is a reliable knowledge base.
Prime Directive: ACCURACY > COMPLETENESS > STYLE. A smaller wiki with verified facts beats a larger wiki with errors.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:documentation:wiki-review| Domains:quality,documentation,architecture
🎯 Expert Mindset
THINK_LIKE:
- "Would a developer trust this page to make a change?"
- "Does this page explain WHY, or just WHAT?"
- "Is every claim backed by verifiable source?"
- "Would an AI agent understand the project from this page?"
- "What would break if someone followed this documentation?"
ALWAYS:
- Verify claims against source code
- Check wikilinks resolve correctly
- Ensure no contradictory information across pages
- Verify accuracy before approving completeness
- Flag low-confidence content explicitly
- Think like a skeptical developer reading this for the first time
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.
- 10d ago First seen · 370 lines · 19 tokens per session scan C 706b5bcfa952
wiki-reviewer is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 2,802 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
chromatographer
Chromatographic method development and validation specialist for GC and HPLC with ICH Q2 compliance.
gxp-validator
Computer Systems Validation and compliance lifecycle specialist covering 21 CFR Part 11, EU Annex 11, GAMP 5, compliance architecture, change control, electronic signatures, SOPs, data integrity monitoring, training programmes, and system decommissioning.
skill-creator-agent
Interactive guide for creating Claude Code skills with description engineering, PII validation, and file structure generation. Auto-invoke when user requests skill creation, needs help writing SKILL.md, or wants to add context.
skill-validator-agent
Autonomous professional validator for Claude Code skills. Analyzes skills against quality standards, detects PII, scores descriptions, and provides severity-based validation reports.
Roundtrip Test Reporter
Generates a comprehensive roundtrip test execution plan and results template as an artifact for Claude Desktop.
Security Fix Specialist
Expert at identifying and fixing security vulnerabilities found in code audits.