agentmods.dev

multi-reviewer

multi-reviewer is a skill for Claude Code from gylove1994/superpowers-deepseek-v4. It costs 90 tokens per session (1,739 once invoked), scanned A, original, MIT.

A review workflow that sends a draft specification or plan to several reviewers with different focuses, then combines their findings.

In plain words
What is it for?
Use it to review a software specification or implementation plan through multiple review rounds until the findings are resolved or assessed.
Why use it?
It exposes architecture problems, overlooked edge cases, unnecessary work, and testing gaps before implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the superpowers-deepseek-v4 plugin — 19 skills, 1 hook shipped together

not rated 10repo 1mo ago A scan 90 tokens original MIT

Good fit Use it to review a software specification or implementation plan through multiple review rounds until the findings are resolved or assessed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gylove1994/superpowers-deepseek-v4/multi-reviewer
View source ↗ gylove1994/superpowers-deepseek-v4
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.

Any agent
npx skills add gylove1994/superpowers-deepseek-v4 --skill multi-reviewer
Clone the repo
git clone --depth 1 https://github.com/gylove1994/superpowers-deepseek-v4

Made for: Claude Code.

Or install superpowers-deepseek-v4, the plugin that ships this one along with the rest of its 19 skills, 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 multi-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/multi-reviewer/github.svg)](https://agentmods.dev/skills/gylove1994/superpowers-deepseek-v4/multi-reviewer)
Your own site
<a href="https://agentmods.dev/skills/gylove1994/superpowers-deepseek-v4/multi-reviewer"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/multi-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 multi-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/gylove1994/superpowers-deepseek-v4/multi-reviewer"><img src="https://agentmods.dev/badge/skills/gylove1994/superpowers-deepseek-v4/multi-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,739 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 $0.00090 $0.01739
Opus 5 $0.00045 $0.00870
Sonnet 5 $0.00018 $0.00348
Haiku 4.5 $0.00009 $0.00174

Measured 12d ago against content hash 8c857b2880da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

multi-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 12d 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.

skills/multi-reviewer/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Reviewer Subsystem

When to invoke

This SKILL is invoked by:

  • The refactored brainstorming SKILL after its Phase B draft is written.
  • The refactored writing-plans SKILL after its plan draft is written.

It is not invoked by the user directly.

Announce at start: "I'm using the multi-reviewer subsystem to run round N of review."

What you (the main flow agent) must do

You play two roles during this loop:

  • Controller — Dispatch reviewer and arbiter subagents, collect outputs, update the decision-log / plan-progress file.
  • DS — When the arbiter returns CONTINUE, you revise the draft.

Subagents have isolated contexts and do not see your conversation history.

The loop

Implements the pseudocode in convergence-rules.md. Each iteration:

1. Compute reviewer dispatch list

  • Always include: architect, red-team, edge-cases, yagni-gatekeeper, bdd-reviewer, tdd-reviewer.
  • Plus: one exemplar-matcher per matched sample (0, 1, or 2). Total reviewer count is 6, 7, or 8.

2. Update the decision-log / plan-progress file

Before dispatching, in the file's "Round N" subsection, write:

  • Dispatched reviewers list (with sample assignment for exemplar-matchers).
  • Receipt status table: all reviewers as ⏳ waiting.

(The file path is provided to you by the calling SKILL — either a *-brainstorm.md for brainstorming Phase B, or a *-plan-progress.md for writing-plans.)

3. Dispatch all reviewers in parallel

Issue all N reviewer Task invocations in the same message batch. Each invocation gets:

  • The reviewer prompt from reviewer-prompts/<role>.md.
  • The current draft (full text).
  • The reviewer's reviewer_role.
  • For exemplar-matcher only: the assigned sample's filename + full content.
  • document_type selection: brainstorming Phase B → spec-draft; writing-plans → plan-draft. Invalid or missing enum → receipt ✗ failed (re-dispatch once, then exclude per §4).
  • Preamble for every reviewer: document_type as above.
  • For bdd-reviewer on plan-draft: include source_spec_path + full source spec text.
  • For tdd-reviewer on plan-draft: include source_spec_path + full source spec ## Testing Strategy section text; if section absent, pass testing_strategy_absent: true and tdd-reviewer applies spec §C.1 BLOCKING against source spec.
  • Load prompts from reviewer-prompts/bdd-reviewer.md and reviewer-prompts/tdd-reviewer.md.

Read the full file on GitHub · 124 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 124 lines · 90 tokens per session scan A 8c857b2880da

Subscribe to this mod's changes

multi-reviewer is a skill published in the GitHub repository gylove1994/superpowers-deepseek-v4 (10 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,739 once invoked, about $0.0005 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.

Code reviewPlanning
Related

Other skills, from other repositories

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens