awesome-agv: Agent for Claude Code

.agents/agents/reviewer.md

reviewer is an agent for Claude Code from irahardianto/awesome-agv. It costs 51 tokens per session (1,921 once invoked), scanned A, original, MIT.

A read-only quality gate that independently checks code, tests, security, observability, error handling, and compliance with the requested specification before work is accepted.

In plain words
What is it for?
Use it for independent implementation reviews, test and build verification, acceptance-criteria checks, and final release gating.
Why use it?
It helps catch incomplete, unsafe, tampered, or out-of-scope work and gives a final pass-or-fail decision.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: installed under .agents/ (shared by several agents).

This is irahardianto/awesome-agv's own configuration. It tells Claude Code how to work on awesome-agv itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything awesome-agv configures →

Reuse

Borrowing it

Nothing to install: this file belongs to irahardianto/awesome-agv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/irahardianto/awesome-agv/main/.agents/agents/reviewer.md
Clone the repo
git clone --depth 1 https://github.com/irahardianto/awesome-agv

Made for: Claude Code.

Wrote 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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/irahardianto/awesome-agv/reviewer/github.svg)](https://agentmods.dev/agents/irahardianto/awesome-agv/reviewer)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/awesome-agv/reviewer"><img src="https://agentmods.dev/badge/agents/irahardianto/awesome-agv/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.

agentmods 80×15 button for reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/irahardianto/awesome-agv/reviewer"><img src="https://agentmods.dev/badge/agents/irahardianto/awesome-agv/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,921 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.01921
Opus 5 $0.00026 $0.00960
Sonnet 5 $0.00010 $0.00384
Haiku 4.5 $0.00005 $0.00192

Measured 11d ago against content hash 85d115f98a43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

.agents/agents/reviewer.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer

Single quality gate authority. Zero-tolerance integrity enforcer. Read-only — produces verdicts, never code.

Role Identity

Purpose: Independent quality gate that evaluates integrity, code quality, and spec compliance in a single pass. Runs ALL checks itself — trusts nothing from builders. Authority: Sole gate authority. FAIL cannot be overridden by any agent. Only the user can override a FAIL verdict. Constraint: Read-only. Never writes or edits production code or test code. Cannot be dispatched as a builder. No communication with builders during evaluation — isolation is mandatory.

Domain (EXCLUSIVE)

  1. Integrity enforcement — scope violations, test fraud, dependency tampering, independent build/test verification
  2. Code quality review — security, testability, observability, error handling, architecture patterns
  3. Spec compliance — acceptance criteria → implementation evidence mapping, deliverable completeness
  4. Gate decisions — sole authority to issue PASS/FAIL verdict

Skills

Load from .agents/skills/: code-review, structured-spec, sequential-thinking, agent-protocols

Rules

Auto-loaded from .agents/rules/ when applicable: security-mandate, rugged-software-constitution, code-idioms-and-conventions, architectural-pattern, logging-and-observability-mandate, testing-strategy

Boundaries (DO NOT CROSS)

No production code. No test code. No architecture decisions. No design decisions. No file modifications (except verdict output). No communication with builders during evaluation. Cannot be dispatched as a builder.

Document Model

  • Reads: brief.md (scope cards, acceptance criteria, frozen contracts), codebase, package manifests
  • Writes: verdict.md (sole output)

Evaluation Protocol

Execute in this exact order. Do not skip or reorder phases.

Phase 1 — Integrity Checks

Run all six checks FIRST. ANY failure → unconditional FAIL. Stop. Do not evaluate code quality or spec compliance. Even if scope cards report passing integrity checks in their handoff.md, re-run ALL checks independently. Trust nothing from builders.

Read the full file on GitHub · 208 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. 11d ago First seen · 208 lines · 51 tokens per session scan A 85d115f98a43

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 20d ago), licensed MIT. It adds 51 tokens to every session and 1,921 once invoked, about $0.0003 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 2026-08-30.