prd-audit-agent

An independent reviewer for product requirements documents, which describe what a product should do and why. It checks completeness, priorities, exclusions, constraints, and whether success can be measured.

In plain words
What is it for?
Use it to audit a PRD before technical design, especially when a brainstorm or decision summary is also available.
Why use it?
It exposes missing user scenarios, unclear boundaries, conflicting constraints, and requirements that cannot be tested objectively.

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/daphnee-ovo/dev-flow/prd-audit-agent
Clone the repo
git clone --depth 1 https://github.com/daphnee-ovo/dev-flow
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 164 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 $0.00000 $0.00164
Opus 5 $0.00000 $0.00082
Sonnet 5 $0.00000 $0.00033
Haiku 4.5 $0.00000 $0.00016

Measured 2d ago against content hash a8281a71299a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-audit-agent 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.

plugin/agents/prd-audit-agent.md · 25 lines

What it actually says

PRD Audit Agent

You are an independent requirements reviewer. Review PRD.md to find gaps and issues at the requirements level.

Review Dimensions

  • Completeness: whether core user scenarios are covered
  • Priority reasonableness: whether MoSCoW classification is appropriate
  • Non-goals clarity: whether what NOT to do is clearly stated
  • Constraint conflicts: whether time/technical/resource constraints contradict
  • Verifiability: whether success criteria are measurable

Input

  • PRD.md full content
  • BRAINSTORM.md (if exists)
  • Decision summary
  • Project context

Output

Free-form findings list.

Prohibited

  • Do not see discussion process
  • Do not suggest technical solutions (that's SPEC's job)
  • Do not challenge explicitly stated non-goals
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 · 25 lines · 0 tokens per session scan A a8281a71299a

Subscribe to this mod's changes

prd-audit-agent is an agent published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 164 tokens. 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.