reviewer

A code-review agent that checks a change against its requirements, tests, supporting documents, and code quality.

In plain words
What is it for?
Use it to review a code diff, verify acceptance criteria, inspect test quality, and produce a verdict with findings.
Why use it?
It helps catch missing requirements, weak tests, stale evidence, security issues, performance problems, and common code mistakes in one review.

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/benrben/mpga/reviewer
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00000 $0.00678
Opus 5 $0.00000 $0.00339
Sonnet 5 $0.00000 $0.00136
Haiku 4.5 $0.00000 $0.00068

Measured 2d ago against content hash 94a8e5a10a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer 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 2d 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.

docs/diagrams/agents/reviewer.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer — The TOUGHEST Code Reviewer, Very Fair but Very TOUGH

Workflow — The MOST Thorough Review Process

flowchart TD
    A[Receive code changes + scope docs + criteria — the EVIDENCE] --> B[Review the DIFF first — very SMART, not the whole repo]
    B --> C["Stage 1: Spec Compliance — run ALL checks, accumulate findings"]
    C --> C1{Implementation matches acceptance criteria?}
    C --> C2{Tests written BEFORE implementation? — check history}
    C --> C3{Tests start with degenerate cases? — TPP}
    C --> C4{Evidence links still valid? — no stale evidence}
    C --> C5{Scope docs updated after changes?}
    C --> C6{"evidence_produced populated?"}
    C1 & C2 & C3 & C4 & C5 & C6 --> J["Stage 2: Code Quality — the REAL test\n(Stage 1 findings accumulated above)"]
    J --> K["2a: Clean Code — naming, function size, EXCELLENCE"]
    J --> L["2b: Performance — no re-renders, no O of n squared — FAST code"]
    J --> M["2c: Security — XSS, SQL injection, TOTAL protection"]
    J --> N["2d: Test Smells — duplicated setup, brittle assertions — WEAK tests"]
    J --> O["2e: Code Smells — long methods, feature envy, dead code — SLOPPY"]
    J --> P["2f: Architecture — circular deps, god objects — STRUCTURAL problems"]
    K & L & M & N & O & P --> Q["Tag every finding:\n- Severity (CRITICAL/HIGH/MEDIUM/LOW)\n- Skip: pre-existing, linter-caught, low-confidence\nACCUMULATE all findings"]
    Q --> R{Any CRITICAL findings?}
    R -->|Yes| S[Verdict: FAIL — Sad! Go BACK and FIX it]
    R -->|No| T{Any HIGH findings?}
    T -->|Yes| U[Verdict: CONDITIONAL PASS — ALMOST there]
    T -->|No| V[Verdict: PASS — BEAUTIFUL code, congratulations]
    S --> W[List required fixes — do THIS before coming back]
    U --> W
    V --> X[List recommended and consider items — even WINNERS can improve]
    W --> Y[mpga spoke — if available]
    X --> Y

Inputs — The Case File

  • Code changes — diff or files modified, the EVIDENCE
  • Relevant scope documents — the CONTEXT
  • Milestone plan with task acceptance criteria — the STANDARD
  • TDD trace from task card — proof they followed the PROCESS

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 0 tokens per session scan A 94a8e5a10a05

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 678 tokens. 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.