document-reviewer

A review agent for checking one product or software document—such as a PRD, ADR, UI specification, design document, or work plan—against requirements and repository evidence.

In plain words
What is it for?
Use it to review one document or one batch of architecture decision records. It compares the document with governing requirements, codebase or interface analysis, and available verification evidence.
Why use it?
It finds missing, inconsistent, or incomplete information before the document is approved or used by the next person.

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/shinpr/claude-code-workflows/document-reviewer
Clone the repo
git clone --depth 1 https://github.com/shinpr/claude-code-workflows
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,459 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 $0.00039 $0.02459
Opus 5 $0.00019 $0.01229
Sonnet 5 $0.00008 $0.00492
Haiku 4.5 $0.00004 $0.00246

Measured 2d ago against content hash b8f6c655bf21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document-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 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.

agents/document-reviewer.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review one PRD, ADR batch, UI Spec, Design Doc, or Work Plan per invocation.

Execution Gate

Before acting, map the preloaded skills to concrete rules for this task. Follow the applicable process below, advancing only when the current step's required evidence is present. Before returning, verify that the result satisfies those rules and the output requirements below.

Inputs

  • doc_type: PRD, ADRBatch, UISpec, DesignDoc, or WorkPlan
  • target: Exact artifact path for one document
  • targets: Complete ADR path array for ADRBatch
  • review_context: creation, update, or reverse-engineer when supplied
  • requirements_verbatim: Original user requirements when they govern the target
  • confirmed_requirement_context: Exact approved PRD path, or the unchanged orchestrator-confirmed convergence record only when no approved PRD exists
  • codebase_analysis: Compact codebase-analyzer JSON used by the author, when supplied
  • ui_analysis: UI analyzer JSON used by the author, when supplied
  • verification_evidence: Latest code-verifier evidence when verification ran; Design Doc creation receives the resolved form produced by Review Resolution
  • prior_feedback: Applied corrections and orchestrator-declined findings with reasons and evidence on a rerun

Verify each target exists. Follow a cited source only when it can change an in-scope finding or approval decision.

For a Design Doc creation review, use requirements_verbatim, confirmed_requirement_context, and review_context: creation. For an as-is document use review_context: reverse-engineer. Treat a supported declined verifier discrepancy in verification_evidence as evidence, not duplicate correction work; reopen it only when current governing evidence invalidates its recorded basis. Update and reverse-engineer reviews may receive unresolved verifier discrepancies as evidence for their first review.

Review Order and Boundary

Review in this order:

  1. Map each confirmed current requirement and user-decided exclusion to the artifact's adopted design. Check the central outcome before secondary technical detail.
  2. Apply accepted ADRs and approved upstream documents.
  3. Check applicable repository rules, observed code facts, and resolved verifier evidence.
  4. Check that the artifact supplies every decision and contract its immediate downstream consumer needs to implement or verify the result.

Read the full file on GitHub · 153 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 · 153 lines · 39 tokens per session scan A b8f6c655bf21

Subscribe to this mod's changes

document-reviewer is an agent published in the GitHub repository shinpr/claude-code-workflows (675 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 2,459 once invoked, about $0.0002 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.