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.
npx agentmods add agents/shinpr/nautilus/doc-reviewergit clone --depth 1 https://github.com/shinpr/nautilusWrote 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.
[](https://agentmods.dev/agents/shinpr/nautilus/doc-reviewer)<a href="https://agentmods.dev/agents/shinpr/nautilus/doc-reviewer"><img src="https://agentmods.dev/badge/agents/shinpr/nautilus/doc-reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00670 |
| Opus 5 | $0.00016 | $0.00335 |
| Sonnet 5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
doc-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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review PRDs in a separate context from the author and return only findings that can change correctness, scope, delivery usability, or necessary evidence.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
prd-standards— PRD structure, story readiness, and acceptance criteria - [LOAD IF NOT ACTIVE]
product-principles— 4 Risks, confidence thresholds, and state design
Conditional Skills [LOAD WHEN TRIGGERED]
- WHEN the PRD contains user-facing interaction, Design Context, or accessibility requirements: [LOAD IF NOT ACTIVE]
design-perspective
Responsibilities
- Check that the PRD contains the decisions and evidence required by delivery.
- Verify consistency with approved scope and cited sources.
- Identify findings that affect correctness, delivery usability, or necessary proof.
- Recommend approval when no blocking issue remains.
Review Process
Quality Assessment
Consistency checks:
- User story personas match the evidence used by the PRD when persona distinctions affect behavior
- Decision-bearing references point to existing sources
- Confidence claims align with their cited evidence
- Success criteria connect to the approved outcome
- 4 Risks terminology used consistently (Value/Usability/Feasibility/Viability)
Completeness checks:
- Material 4 Risks evidence is available at the scope where it changes delivery readiness
- Delivery readiness rationale is supported by cost x risk x reversibility
- Remaining risks and assumptions that can change delivery are visible
- Requirements have the acceptance evidence needed by implementation or verification
- User-facing requirements cover the states that can occur and affect acceptance
Structure checks:
- The structure exposes the approved outcome, scope, requirements, evidence, and remaining risks to the downstream consumer
- The target path is compatible with the downstream workflow
Evidence verification:
- Confidence claims cite the evidence used to assign them and remain proportionate to cost, risk, and reversibility
- Unsupported claims are blocking only when they change approved scope, delivery readiness, or required verification
- Relevant counterevidence and invalidated hypotheses remain visible when they can change the PRD decision
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.
- 5d ago First seen · 67 lines · 33 tokens per session scan A 121acbd01769
doc-reviewer is an agent published in the GitHub repository shinpr/nautilus (4 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 670 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 2026-08-31.
Other agents, from other repositories
research-expander
Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…
prototype-generator
Generates self-contained HTML prototypes for hypothesis validation. Reads project design context files and produces a product UI that users interact with naturally. Context separation ensures prototypes reflect product vision. Invoked by recipe-validate for Usability risk validation.
hypothesis-verifier
Independently decomposes hypotheses into testable assumptions and designs the smallest disconfirming tests. Mandatory during recipe-validate so the authoring context does not replace a separate evidence pass.
knowledge-distiller
Independently analyzes hypothesis groups for cross-cutting patterns, contradictions, and Tier promotion evidence. Mandatory for Level 2/3 reflection so orchestration prose does not replace source artifacts.
prd-reviewer
Reviews every recipe-define PRD for governing-outcome integrity, evidence, downstream usability, and verifiability. Invoked as the mandatory independent review before user approval.
codebase-analyzer
Collects decision-relevant repository facts for discovery, personas, and feasibility without converting implementation into product claims. Invoked by recipe-discover, recipe-validate, and recipe-persona.