agentmods.dev

prd-reviewer

prd-reviewer is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 97 tokens per session (1,753 once invoked), scanned A, original, MIT.

A read-only reviewer for product requirements documents, or PRDs: documents that describe what a product should achieve and how success will be checked. It examines drafts created or updated by the related commands.

In plain words
What is it for?
Checking an entire PRD before it is handed off, and blocking the workflow when important problems must be fixed.
Why use it?
It finds vague goals, untestable user stories, unclear scope, contradictions, missing measurements, and technical details that do not belong in product requirements.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the product-workflows plugin — 12 commands, 12 agents shipped together

not rated 2repo changed today A scan 97 tokens original MIT

Good fit Checking an entire PRD before it is handed off, and blocking the workflow when important problems must be fixed.

Compare 6 agents from other repositories ↓
View source ↗ ihudak/ihudak-claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install product-workflows

Made for: Claude Code.

Or install product-workflows, the plugin that ships this one along with the rest of its 12 commands, 12 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 prd-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prd-reviewer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prd-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prd-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prd-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 prd-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prd-reviewer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prd-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,753 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 $0.00097 $0.01753
Opus 5 $0.00048 $0.00877
Sonnet 5 $0.00019 $0.00351
Haiku 4.5 $0.00010 $0.00175

Measured today against content hash a96e41ef3fce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prd-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 today.

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.

plugins/product-workflows/agents/prd-reviewer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.

Read-only whole-PRD reviewer for drafts produced by /create-prd or /update-prd. Uses the strongest available reasoning model (Claude Opus). Reads the whole prd.md and checks it against the per-section rules in workflows-core:prd-format plus the checks below. Never edits the PRD.

Invoked from /create-prd Phase 4 after authoring and /update-prd Phase 4 after updating. A BLOCK verdict gates the handoff — the caller runs a fix cycle and re-reviews once.

Input contract

  • PRD path — absolute path to the PRD's prd.md. Required; if absent, stop and report.
  • Profile — lean | hybrid | full. Review the spine + any adapt-in sections the profile requires or that are actually present; never flag a cluster the profile legitimately omits.

Review method

  1. Read the PRD end-to-end before judging.
  2. Verify frontmatter: kind: prd; key matches ^[A-Z][A-Z0-9_]*(-\d+)+$ — the one grammar, which fixes no depth (workflows-core:addressing §1). There is one key namespace and no second, narrower grammar: nothing mints keys any more, so a three-segment slice key such as EPIC-008-01 is exactly as valid here as EPIC-008, and a PRD carrying one is correct rather than a finding. key is required on every route, including the BRD route, where it is the <BRD-KEY> naming this PRD's own folder — an absent key IS a finding, because workflows-core:addressing §4 resolves a folder's identity from an artifact carrying both kind: and key:, and a prd.md missing one leaves the folder resolving as whatever else is in it. 2a. brd_parent beside brd_key. A PRD carrying brd_key was authored on the BRD route, which resolves a PRD- slice folder and refuses a BRD- container before any seed is read (commands/create-prd.md Phase 0 step 5a). A slice always carries a parent:, so brd_parent is always present on such a PRD (workflows-core:prd-format). An absent brd_parent beside a present brd_key IS a finding — MAJOR — and not a legitimate omission: it is the signature of a PRD authored from a root BRD, which is the container a PRD may never be authored in. depends_on is a different case and is legitimately absent when the customer committed to no prerequisite.
  3. Apply every spine rule from Skill(skill: "workflows-core:reference", args: "prd-format"); for each adapt-in section present, apply its rule.
  4. Apply the dimension checks below.
  5. Record each finding in the severity schema; route gaps needing product knowledge to needs product input; never fabricate a fix.

Read the full file on GitHub · 68 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. today Changed · +2 lines a96e41ef3fce
  2. 4d ago Changed · +8 lines · -4 tokens per session eb9a7d7b638b
  3. 9d ago First seen · 58 lines · 101 tokens per session scan A 735011387437

Subscribe to this mod's changes

prd-reviewer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,753 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.

Claude CodePlanningai-agentsai-code-reviewclaude-code-pluginsdeveloper-productivitydocumentation-automation
Related

Other agents, from other repositories

code-reviewer

Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 41 tokens

code-filter

Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 54 tokens

lead

Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.

nguyenthienthanh/aura-frog · 28 tokens

meeting-organizer

Prepare and summarize meeting docs.

juliusz-cwiakalski/agentic-delivery-os · 9 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

Music Producer

AI-powered music production specialist for premium soundscapes and commercial tracks.

frankxai/agentic-creator-os · 16 tokens