prd-audit

prd-audit is a skill for Claude Code, Codex from jstoup111/ai-conductor. It costs 45 tokens per session (3,198 once invoked), scanned A, original, Apache-2.0.

A review skill that checks shipped code against the acceptance criteria in feature stories. It reports each criterion as passed, fixable, a planning gap, or outside the agreed scope.

In plain words
What is it for?
Use it at the end of a feature to audit requirements, record criterion-level findings, and distinguish implementation problems from flaws in the plan or extra work.
Why use it?
It reveals whether the delivered implementation actually meets the agreed behavior, with findings tied to concrete file and line evidence.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Good fit Use it at the end of a feature to audit requirements, record criterion-level findings, and distinguish implementation problems from flaws in the plan or extra work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jstoup111/ai-conductor/prd-audit
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 jstoup111/ai-conductor --skill prd-audit
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/jstoup111/ai-conductor/prd-audit/github.svg)](https://agentmods.dev/skills/jstoup111/ai-conductor/prd-audit)
Your own site
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/prd-audit"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/prd-audit/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-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/prd-audit"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/prd-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,198 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 9
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00045 $0.03198
Opus 5 $0.00023 $0.01599
Sonnet 5 $0.00009 $0.00640
Haiku 4.5 $0.00005 $0.00320

Measured yesterday against content hash 3fd9883ca6da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prd-audit 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 yesterday.

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/prd-audit/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

At SHIP, judge whether the implementation was built as the feature stories specify. The stories' acceptance criteria are the authority. PRD functional requirements are intent context when a PRD exists; the plan's stated outcome is also intent context. This is a finding-authority: report grounded judgement and do not implement, amend DECIDE artifacts, append remediation tasks, or choose the gate route. The engine owns those mechanical outcomes.

Each finding carries exactly one grade: PASS | FIXABLE | PLAN_GAP | OVER_SCOPE. Verdict Table findings are keyed to active story criteria; no-owner OVER_SCOPE findings are keyed as NC.<n> in their dedicated section below. The engine rejects malformed rows with a diagnostic while retaining valid sibling rows. Never invent a key (OS.1, SCOPE.2) or write duplicate rows for one key.

Every Verdict Table key must be an id of an active story criterion. Use the form S<story>.<criterion>; do not use NC.<n> in the Verdict Table. A well-formed story key that names no criterion in the active stories is also invalid.

<story> is the story's heading id verbatim, not just its digits — ## Story 5a: owns S5a.1, S5a.2, … and ## Story 2.1: owns S2.1.1, S2.1.2, …, each distinct from Story 5's and Story 2's. <criterion> is always the numeric ordinal. Keys are matched case-insensitively.

Per the /verify-claims protocol, cite concrete file:line evidence and give a confidence when evidence is ambiguous. Do not turn uncertainty into a PASS.

Run at SHIP alongside the other SHIP validators. The configured step decides whether it is enabled; this skill does not infer a skip from feature tier, track, or the absence of a PRD.

Inputs and authority

  1. Resolve the feature's committed stories through the active plan's **Stories:** reference. Read every happy and negative criterion. If criteria cannot be read, report a BLOCKED audit that names the stories file; never pass by default.
  2. Read the active plan, including its stated outcome and task ownership. Where a committed coherence mapping exists, use it to understand criterion-to-intent traceability.
  3. Read the matching non-SUPERSEDED- PRD when present. Its FRs explain intent; they do not replace story criteria as the audit key. A PRD requirement without story coverage is a PLAN_GAP finding against that requirement's missing criterion/traceability, not a silently omitted FR.
  4. Read the implementation, changed tests, and relevant BUILD Scope: trailers. Trace each criterion to concrete behavior or its absence.

Read the full file on GitHub · 201 lines

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. yesterday Changed · +43 lines 3fd9883ca6da
  2. 2d ago Changed · +4 lines fe1fb6e6e272
  3. 4d ago Changed · +11 lines ea57c585c2a4
  4. 5d ago Changed · +4 lines e34828ee4047
  5. 9d ago First seen · 139 lines · 45 tokens per session scan A 0e1e2a906075

Subscribe to this mod's changes

prd-audit is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 3,198 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens