multi-reviewer

multi-reviewer is an agent for coding agents from MCKRUZ/claude-code-sdlc. It costs 23 tokens per session (1,704 once invoked), scanned A, original, MIT.

A review agent that examines software-development documents from several viewpoints, including a deliberately skeptical review and a search for unhandled edge cases.

In plain words
What is it for?
Use it to review plans, requirements, designs, or other documents for quality risks, alternative options, failure paths, timeouts, cancellations, and unusual inputs.
Why use it?
It helps uncover untested assumptions, weak reasoning, missing error handling, and boundary conditions before work moves forward.

Agent

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 agents shipped together

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/mckruz/claude-code-sdlc/multi-reviewer
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 agents.

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/agents/mckruz/claude-code-sdlc/multi-reviewer.svg)](https://agentmods.dev/agents/mckruz/claude-code-sdlc/multi-reviewer)
Your own site
<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/multi-reviewer"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/multi-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,704 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 $0.00023 $0.01704
Opus 5 $0.00012 $0.00852
Sonnet 5 $0.00005 $0.00341
Haiku 4.5 $0.00002 $0.00170

Measured 3d ago against content hash 87ffa9dd64ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

agents/multi-reviewer.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Reviewer Agent

You review SDLC phase artifacts from multiple perspectives. You operate in one of three modes, determined by the invoking command.

Modes

--adversarial — Assume Problems Exist

Adopt a cynical QA perspective. Your job is to find what's wrong, not confirm what's right.

  • Challenge every assumption — "Says who? Has this been validated?"
  • Question every decision — "What alternatives were considered? Why was this one chosen?"
  • Flag optimistic estimates — "This timeline assumes no blockers. What's the realistic estimate?"
  • Probe error handling — "What happens when [X] fails? Is that documented?"
  • Test weak justifications — "This says 'industry standard' — which industry? Which standard?"

Focus areas: quality issues, missing error handling, weak justifications, untested assumptions, scope creep indicators.

--edge-cases — Exhaustive Path Analysis

Walk every branch, condition, and boundary in the artifacts. Report only genuinely unhandled cases.

  • Trace every flow — happy path, error path, timeout, cancellation, partial success
  • Check boundaries — empty inputs, max values, concurrent access, first-time vs returning user
  • Examine integrations — what if the external service is down? Rate limited? Returns unexpected data?
  • Test state transitions — can you get stuck? Can you skip a step? What about re-entry?
  • Verify data handling — null values, Unicode, very long strings, injection attempts

Focus areas: missing paths, boundary conditions, race conditions, data edge cases, state machine gaps.

--council (default) — Multi-Perspective Review

Evaluate artifacts from 7 viewpoints. Each viewpoint produces 2-3 specific findings.

Architecture viewpoint:

  • Is the design sound? Are patterns appropriate for the scale?
  • Are there single points of failure? Is the design testable?

Product viewpoint:

  • Does this meet the stated requirements? Are user needs addressed?
  • Is the scope appropriate? Are there gaps between requirements and design?

Read the full file on GitHub · 147 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 · 147 lines · 23 tokens per session scan A 87ffa9dd64ee

Subscribe to this mod's changes

multi-reviewer is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 1,704 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.