audit-prd

audit-prd is a skill for Claude Code, Codex from cdeust/ai-architect-mcp-spec. It costs 51 tokens per session (255 once invoked), scanned A, original, MIT.

A checker for a multi-section PRD, or product requirements document. It tests the document's structure and links between requirements, acceptance criteria, estimates, and tests.

In plain words
What is it for?
Use it to audit a complete PRD for structural consistency. It can check whether functional requirements map to acceptance criteria and whether stories and tests are traceable.
Why use it?
It finds missing coverage, numbering problems, calculation errors, and broken traceability before the PRD is used by a team. It reports issues without rewriting the document.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ai-architect-mcp-spec plugin — 3 skills, 1 command, 2 MCP servers shipped together

Good fit Use it to audit a complete PRD for structural consistency. It can check whether functional requirements map to acceptance criteria and whether stories and tests are traceable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cdeust/ai-architect-mcp-spec/audit-prd
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.

Any agent
npx skills add cdeust/ai-architect-mcp-spec --skill audit-prd
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-spec

Made for: Claude Code, Codex.

Or install ai-architect-mcp-spec, the plugin that ships this one along with the rest of its 3 skills, 1 command, 2 MCP servers.

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 audit-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-spec/audit-prd/github.svg)](https://agentmods.dev/skills/cdeust/ai-architect-mcp-spec/audit-prd)
Your own site
<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp-spec/audit-prd"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-spec/audit-prd/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 audit-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp-spec/audit-prd"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp-spec/audit-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 255 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 $0.00051 $0.00255
Opus 5 $0.00026 $0.00128
Sonnet 5 $0.00010 $0.00051
Haiku 4.5 $0.00005 $0.00026

Measured 10d ago against content hash 1f190b1a7281, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-prd 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 10d 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.

skills/audit-prd/SKILL.md · 20 lines

What it actually says

Audit a PRD

Use the prd-spec-verifier MCP server to produce an evidence-based structural audit.

Workflow

  1. Read the complete PRD without rewriting it.
  2. Split it into sections and map each section to the closest section_type accepted by the validate_prd_document tool schema. Ask for clarification when a mapping is genuinely ambiguous.
  3. Call validate_prd_document once with every mapped section, preserving content exactly.
  4. Report each violation with its rule identifier, severity, affected section, and the evidence returned by the tool.
  5. Group repeated findings and distinguish blocking violations from warnings.
  6. State the scope limit: a passing report demonstrates conformance to the implemented structural rules only. It does not establish factual accuracy, product value, implementation feasibility, security, or semantic correctness.

Do not invent a pass for checks the tool did not run. Do not silently repair the PRD unless the user also asks for edits.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 20 lines · 51 tokens per session scan A 1f190b1a7281

Subscribe to this mod's changes

audit-prd is a skill published in the GitHub repository cdeust/ai-architect-mcp-spec (3 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 255 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

live-audit

Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…

Grinv/steam-games-mcp · 83 tokens

prompt-check

Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.

Grinv/steam-games-mcp · 54 tokens

add-test

Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.

open-metadata/ai-sdk · 40 tokens

run-integration

Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AISDKHOST, AISDKTOKEN) and runs tests that make actual API calls.

open-metadata/ai-sdk · 40 tokens

field-test

Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…

cyanheads/pubchem-mcp-server · 76 tokens

add-test

Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.

cyanheads/pubchem-mcp-server · 41 tokens