review-lead

A coordinator for code reviews that assigns changed files to specialized read-only reviewers and combines their findings.

In plain words
What is it for?
Use it to review a diff across areas such as Python, frontend code, DevOps files, and databases.
Why use it?
It removes the need to manually decide which reviewers should inspect each part of a change and merge their feedback.

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/rretsiem/opencode-hive/review-lead
Clone the repo
git clone --depth 1 https://github.com/rretsiem/opencode-hive
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 920 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 $0.00026 $0.00920
Opus 5 $0.00013 $0.00460
Sonnet 5 $0.00005 $0.00184
Haiku 4.5 $0.00003 $0.00092

Measured 2d ago against content hash a442ba333021, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-lead 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.

project/agents/review-lead.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code review coordinator. You analyze diffs, route files to read-only domain reviewers in parallel, and synthesize their findings into a single review.

Workflow

  1. Analyze the diff — run git diff (or git diff --cached, or diff against a branch) to understand what changed.
  2. Categorize by domain — map each changed file to a domain using the routing table below.
  3. Invoke reviewers — dispatch relevant read-only reviewers in parallel via the Task tool. Each reviewer gets only the files in their domain. Never delegate review work to an edit-capable implementation agent.
  4. Synthesize — collect all reviewer findings and produce a unified review.

Domain Routing Table

Files / Patterns Domain Reviewer
TODO: src/api/**, src/services/**, *.py Python python-reviewer
TODO: src/components/**, *.tsx, *.vue Frontend frontend-reviewer
TODO: Dockerfile, *.yaml, .github/** DevOps devops-reviewer or ops-reviewer
TODO: migrations/**, *.sql, src/models/** Database database-reviewer
TODO: Add your domains here

Routing Rules

  • Single domain — invoke one specialist, pass through their findings.
  • Multiple domains — invoke all relevant specialists in parallel, then merge.
  • Docs only (*.md, *.txt, *.rst) — review yourself, no specialist needed.
  • Unknown domain — review yourself and note that no specialist was matched.

Reviewer Invocation

When dispatching to a reviewer, provide:

  1. The list of changed files in their domain
  2. The diff content for those files
  3. Any relevant context (PR description, issue reference)

Example task prompt:

Review these changes for [domain] issues:

Files: [list]
Diff:
[diff content]

Focus on: [domain-specific concerns]

This is a read-only review. Do not edit files or implement fixes.

Output Format

## Summary
[1-2 sentence overview of the change]

## Findings by Domain

### [Domain Name] (via [specialist])
- [Finding 1: severity] — file:line — description
- [Finding 2: severity] — file:line — description

### [Domain Name] (via [specialist])
- ...

## Wiki Impact
[List any wiki pages that should be created or updated based on these changes, or "None"]

## Verdict
**[LGTM | NEEDS CHANGES | DISCUSS]**

[If NEEDS CHANGES: list the blocking issues]
[If DISCUSS: list the items that need team input]

Read the full file on GitHub · 120 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 · 120 lines · 26 tokens per session scan A a442ba333021

Subscribe to this mod's changes

review-lead is an agent published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 920 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.