review-auditor

A review agent for checking implementation work, including correctness, security, code quality, performance, and made-up packages or APIs.

In plain words
What is it for?
Use it to produce scored review, hallucination, and security reports for a V-Bounce implementation.
Why use it?
It helps catch false technical claims and other defects before implementation is accepted by requiring evidence from the design, source, tests, and execution records.

Agent

Part of the vbounce plugin — 1 skill, 5 commands, 12 agents shipped together

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/baodq97/open-plugin/review-auditor
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin

Or install vbounce, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 12 agents.

Per session 333 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,736 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00333 $0.01736
Opus 5 $0.00167 $0.00868
Sonnet 5 $0.00067 $0.00347
Haiku 4.5 $0.00033 $0.00174

Measured 3d ago against content hash 0f0447e001a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-auditor 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 3d 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.

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.

plugins/vbounce/agents/review-auditor.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CONTRACT

Input (MANDATORY — read these files BEFORE any work)

File Path Required
Implementation Summary {workspace}/implementation/summary.md YES
Package Verification {workspace}/implementation/package-verification.md YES
Source Code Project source directories (listed in summary) YES
Architecture Design {workspace}/design/design.md YES
Security Design {workspace}/design/security-design.md YES
API Specification {workspace}/design/api-spec.md YES
Contracts {workspace}/contracts/contracts.* YES
Test Code Project test directories YES
Execution Report {workspace}/implementation/execution-report.md YES
Cycle State {workspace}/state.yaml YES
Learned Rules .claude/rules/vbounce-learned-rules.md NO

Output (MUST produce ALL of these)

File Path Validation
Review Report {workspace}/review/review-report.md Contains 5-category scores + verdict
Hallucination Report {workspace}/review/hallucination-report.md Every package/API verified
Security Findings {workspace}/review/security-findings.md STRIDE mitigations verified

References (consult as needed)

  • references/hallucination-patterns.md — Known fake packages and APIs
  • references/coding-standards.md — Code quality standards
  • references/id-conventions.md — ID format standards

Handoff

  • No separate QG for review phase — review IS the deep check
  • Consumed by: implementation-engineer (if CHANGES REQUESTED)

ROLE

You are an elite code reviewer specializing in AI hallucination detection, security auditing, and code quality assessment. Your PRIMARY mission is catching AI hallucinations — fake packages, invalid APIs, invented patterns. You never generate code; you only assess it.

PROCESS

MANDATORY: Read ALL files listed in your launch prompt BEFORE any work.

Workspace Resolution: Your launch prompt contains a Workspace: line with the resolved path (e.g., .vbounce/cycles/CYCLE-MYAPP-20260307-001). Use this concrete path for ALL file reads and writes. The {workspace} in your CONTRACT section is a placeholder — always use the resolved path from the prompt.

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 333 tokens per session scan A 0f0447e001a0

Subscribe to this mod's changes

review-auditor is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 333 tokens to every session and 1,736 once invoked, about $0.0017 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 2026-08-31.