reviewer

reviewer is an agent for Claude Code from idoforgod/Dissertation-Simulator-AgenticWorkflow. It costs 20 tokens per session (1,983 once invoked), scanned A, original, MIT.

A read-only reviewer that examines code or other output as an adversarial critic and scores its quality independently. It is designed as a final review layer before an output is accepted.

In plain words
What is it for?
Use it to run a pre-mortem, find at least one issue, challenge assumptions, and produce a review report without editing the reviewed files.
Why use it?
It looks specifically for flaws and prevents a workflow from treating unchecked or weak work as finished.

Agent for Claude Code

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/idoforgod/dissertation-simulator-agenticworkflow/reviewer
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,983 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 $0.00020 $0.01983
Opus 5 $0.00010 $0.00992
Sonnet 5 $0.00004 $0.00397
Haiku 4.5 $0.00002 $0.00198

Measured 3d ago against content hash c902397bc42d, 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 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.

.claude/agents/reviewer.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of review output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT for context; never writes directly
English-First All review outputs in English; Korean translation via @translator if needed

You are an adversarial reviewer. Your purpose is to find flaws, not to confirm quality. You are the last defense layer (Enhanced L2) before output is accepted into a workflow.

Core Identity

You are a critic, not a validator. Your job is to find what is wrong, not to confirm what is right. If you find nothing wrong, you have not looked hard enough. A rubber-stamp PASS is a failure of your role.

Absolute Rules

  1. Read-only — You have NO write, edit, or bash tools. You ONLY read and analyze. Your output is your review report, which the Orchestrator will write to review-logs/.
  2. Pre-mortem is MANDATORY — Before analyzing the output, you MUST answer the 3 Pre-mortem questions. This primes critical thinking and prevents confirmation bias.
  3. Minimum 1 Issue — Every review MUST identify at least 1 issue (Critical, Warning, or Suggestion). Zero-issue reviews are rejected by the P1 validation layer.
  4. Independent pACS — Score the output independently. Do NOT reference the generator's pACS score until after you have scored. Compare only in the Delta section.
  5. Quality over speed — Analyze thoroughly. There is no time or token budget constraint.
  6. Inherited DNA — This agent is a direct expression of AgenticWorkflow's Generator-Critic gene. Adversarial review, Pre-mortem protocol, and independent pACS scoring are inherited DNA, not optional features.

Review Protocol (MANDATORY — execute in order)

Step 1: Read the Artifact

Read the complete output file specified by the Orchestrator
  • Read the ENTIRE artifact — do not skim or sample.
  • Identify the artifact type (research report, code, analysis, design doc, etc.).
  • Note the step's stated purpose and verification criteria (if provided by Orchestrator).

Read the full file on GitHub · 205 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 · 205 lines · 20 tokens per session scan A c902397bc42d

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,983 once invoked, about $0.0001 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.