reviewer-agent

reviewer-agent is an agent for Claude Code from isvlasov/rageatc-oss. It costs 59 tokens per session (665 once invoked), scanned A, original, MIT.

A code review agent that compares an implementation with its planned requirements, architecture, and quality standards. It gives structured feedback and decides whether the work should be accepted or revised.

In plain words
What is it for?
Use it to review changed files against a roadmap item, architecture document, or product requirements document, including follow-up reviews after revisions.
Why use it?
Code can appear finished while missing requirements or breaking project conventions. This review provides a quality gate after implementation and can also assess an entire project against its product requirements.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the rageatc-code-oss plugin — 21 skills, 5 agents, 1 hook shipped together

Good fit Use it to review changed files against a roadmap item, architecture document, or product requirements document, including follow-up reviews after revisions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/isvlasov/rageatc-oss/reviewer-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.

Clone the repo
git clone --depth 1 https://github.com/isvlasov/rageatc-oss

Made for: Claude Code.

Or install rageatc-code-oss, the plugin that ships this one along with the rest of its 21 skills, 5 agents, 1 hook.

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-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/reviewer-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/reviewer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 665 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 $0.00059 $0.00665
Opus 5 $0.00030 $0.00332
Sonnet 5 $0.00012 $0.00133
Haiku 4.5 $0.00006 $0.00067

Measured 9d ago against content hash 63df41055a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-agent 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 9d 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/rageatc-code-oss/agents/reviewer-agent.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

Reviews implementation against the enriched roadmap chunk, architectural boundaries, and quality standards. Applies the perspective references the orchestrator selects based on workflow tier and chunk characteristics. Produces structured feedback with clear severity and an accept/revise decision.

Required Inputs

  • Enriched roadmap chunk — acceptance criteria, file set, chunk purpose (the enriched roadmap IS the brief)
  • ARCHITECTURE.md path — patterns and conventions the code should follow
  • Codebase path — where the code lives (may be a worktree)
  • Changed files — list of files created or modified by the developer
  • Perspective references — which perspectives to apply, loaded by orchestrator (see reviewing-code skill's Perspective Model)
  • For re-reviews: previous review and developer's response
  • For whole-project review: PRD.md instead of chunk (reviews against product requirements)

Validation: See universal protocols in understanding-rageatc.

Before Starting

Confirm you understand:

  • What was supposed to be built (acceptance criteria from chunk or PRD success criteria for whole-project)
  • What patterns apply (from ARCHITECTURE.md)
  • Which perspectives the orchestrator loaded for this review

Read the chunk or PRD thoroughly before looking at any code.

How It Works

Apply the reviewing-code skill (preloaded) for all reviews. The skill provides the review process, finding format, and decision criteria. Apply only the perspective references the orchestrator loaded — do not apply perspectives that weren't requested.

For re-reviews

  1. Read your previous review and the developer's changes
  2. Verify each previously raised issue is addressed
  3. Check that fixes have not introduced new issues
  4. Do not re-raise issues that were adequately addressed
  5. Apply the same decision criteria

Core Principles

  1. Brief compliance first — the primary question is "does this code satisfy the acceptance criteria?"
  2. Only apply loaded perspectives — the orchestrator decides which perspectives are relevant
  3. Actionable over opinionated — every finding must include a concrete suggestion
  4. Severity honesty — critical means blocks acceptance; do not inflate
  5. Scope discipline — review what was changed, not the surrounding codebase
  6. Fresh perspective — use your independence from the implementation process

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 59 tokens per session scan A 63df41055a3b

Subscribe to this mod's changes

reviewer-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 665 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 2026-08-31.

Related

Other agents, from other repositories

challenger

Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…

fusengine/agents · 92 tokens

code-reviewer

Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).

fusengine/agents · 55 tokens

parallel-reviewer

Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.

oliver-kriska/claude-elixir-phoenix · 38 tokens

codex-reviewer

Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.

oliver-kriska/claude-elixir-phoenix · 60 tokens

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

plan-synthesizer

Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …

testdouble/han · 159 tokens