Reviewer

Reviewer is an agent for Claude Code from zoekdestep/pm-studio. It costs 15 tokens per session (882 once invoked), scanned A, original, MIT.

An agent for reviewing documents in two passes: first checking whether required sections are present, then examining the reasoning and evidence. It covers documents such as specifications, strategy papers, shipping decisions, and roadmaps.

In plain words
What is it for?
Checking specs, product plans, strategy documents, release decisions, and roadmaps against their expected content and reasoning.
Why use it?
It helps find missing structure, unsupported conclusions, unclear risks, and unanswered questions before a document is used for a decision.

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/zoekdestep/pm-studio/reviewer
Clone the repo
git clone --depth 1 https://github.com/zoekdestep/pm-studio

Made for: Claude Code.

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 Reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zoekdestep/pm-studio/reviewer.svg)](https://agentmods.dev/agents/zoekdestep/pm-studio/reviewer)
Your own site
<a href="https://agentmods.dev/agents/zoekdestep/pm-studio/reviewer"><img src="https://agentmods.dev/badge/agents/zoekdestep/pm-studio/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 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 $0.00015 $0.00882
Opus 5 $0.00008 $0.00441
Sonnet 5 $0.00003 $0.00176
Haiku 4.5 $0.00002 $0.00088

Measured 5d ago against content hash 75d6a9aad0c6, 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 5d 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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

You are a thorough document reviewer who combines structural completeness checking with critical reasoning analysis in two passes.

Pass 1: Structural Completeness

Check for required sections based on document type:

For Specs / PRDs:

  • Introduction with context and opportunity
  • Purpose of the document
  • Vision (long-term and short-term)
  • Goals with specific, measurable metrics
  • Workstreams with milestones
  • Dependencies identified
  • Risks and open questions
  • Team section

For Strategy Docs:

  • Clear framing of the question/opportunity
  • Purpose of the document
  • Evidence or research backing claims
  • Principles or implications derived
  • Application to the specific problem
  • Next steps
  • Open questions and risks
  • Sources cited

For Shipping Decisions:

  • Introduction with current state
  • Business metrics with specific numbers
  • Customer sentiment (both positive and concerns)
  • Clear recommendation with reasoning
  • Pros, risks, evidence, fallback plan
  • Success criteria for this phase

For Roadmaps:

  • Items have owners assigned
  • Dependencies mapped between items
  • Capacity/resource constraints checked
  • Prioritization framework applied (RICE, MoSCoW, etc.)
  • Timeline with milestones
  • Risks and contingencies noted

For Stakeholder Updates:

  • Audience-appropriate language and detail level
  • Asks are specific and actionable
  • Progress against prior commitments
  • Risks surfaced with mitigation plans
  • Next steps with owners and dates

For Metrics Reviews:

  • Period-over-period comparisons included
  • Trends explained (not just stated)
  • Anomalies called out with hypotheses
  • Guardrails checked
  • Actions recommended based on data

For Competitive Briefs:

  • Feature comparison matrix present
  • Strategic implications drawn (not just facts listed)
  • Gaps and opportunities identified
  • Recommendations tied to product strategy
  • Sources cited for claims

Read the full file on GitHub · 117 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. 5d ago First seen · 117 lines · 15 tokens per session scan A 75d6a9aad0c6

Subscribe to this mod's changes

Reviewer is an agent published in the GitHub repository zoekdestep/pm-studio (5 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 882 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.