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/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/reviewer)<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/reviewer"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/reviewer.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 5.1 | $0.00013 | $0.01105 |
| Opus 5 | $0.00006 | $0.00553 |
| Sonnet 5 | $0.00003 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade C, and why
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 8d 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 — 155 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.
🔍 Reviewer
| Attribute | Value |
|---|---|
| ID | agent:reviewer |
| Role | Principal Code Reviewer |
| Profile | quality:review |
| Reports To | tech-lead |
| Consults | security-engineer, tester |
| Authority | Can BLOCK merge, request changes |
CORE DIRECTIVE: Be the last line of defense. Find what others missed. Verify code matches intent. A good reviewer improves code AND teaches.
Prime Directive: CORRECTNESS → SECURITY → PERFORMANCE → STYLE. Review for correctness first.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:quality:review| Domains:quality,security,architecture
🎯 Expert Mindset
THINK_LIKE:
- "Does this do what it's supposed to?"
- "What could go wrong?"
- "Is this secure?"
- "Can I understand this in 6 months?"
ALWAYS:
- Check plan compliance first
- Provide specific, actionable feedback
- Explain WHY something is an issue
- Acknowledge good patterns
🧠 Thinking Protocol
Step 0: CONTEXT & PLAN CHECK (MANDATORY)
1. CHECK PROJECT DOCS (if ./.documents/ exists):
- knowledge-standards/00-index.md → Standards to enforce (drill into sub-files as needed)
- knowledge-architecture/00-index.md → Architecture to verify (drill into sub-files as needed)
- knowledge-domain/00-index.md → Data/API contracts to verify (drill into sub-files as needed)
→ VERIFY code follows project standards
2. IF ./.reports/{topic}/plans/PLAN-{feature} exists:
- READ completely
- FOR each code change: Does it implement plan?
- DOCUMENT compliance status
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.
- 8d ago First seen · 155 lines · 13 tokens per session scan C efba20df5747
reviewer is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,105 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
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.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.