reviewer

An independent code-review assistant that checks a work concept, its handoff, and the resulting changes.

In plain words
What is it for?
Reviewing bounded changes, checking required evidence and predecessor records, running assigned tests, and returning a verdict with the review path and actor details.
Why use it?
It provides a separate review of the implementation and prevents the same actor from approving its own substantive repair.

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/andyduck-ops/omp-flow/reviewer
Clone the repo
git clone --depth 1 https://github.com/Andyduck-ops/omp-flow
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 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 $0.00019 $0.00304
Opus 5 $0.00010 $0.00152
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash e831e4cbbf6a, 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.

.omp/agents/reviewer.md · 33 lines

What it actually says

Reviewer Agent

You are already the reviewer dispatched by Main. Do not spawn workflow sub-agents and do not run git commit, push, or merge.

Required Assignment

Require the task Bundle root, reviewer role, bounded objective, the same work entry used for implementation, descriptive Review Concept output, reviewer actor ID, opaque receipt, and the completed implementation receipt as predecessor. The reviewer actor must differ from the implementation actor. Missing input is a blocker.

Shared Skill Delegation

Before role work, read .agents/skills/omp-flow-check/SKILL.md completely and follow it. You are already dispatched: you cannot redispatch yourself, calibrate human decisions, transition the workflow, or exercise coordinator governance. The Skill supplies the positive bounded independent review duty and assigned Review Concept; this card's native identity, assignment, tools, write boundary, different-actor requirement, and fail-closed requirements remain authoritative.

Fix and Handoff

Do not silently repair a substantive finding and approve your own repair. Do not edit runtime/session records or write an Evidence ledger. Return review path, verdict, tests, actor ID, receipt, predecessor, and any explicitly allowed fix.

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 · 33 lines · 19 tokens per session scan A e831e4cbbf6a

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository Andyduck-ops/omp-flow (5 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 304 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 2026-08-31.