prd-lint

prd-lint is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (1,934 once invoked), scanned A, original, MIT.

A validator for Product Requirements Documents. It checks both their structure and their meaning, including missing information and requirements that contradict each other.

In plain words
What is it for?
Use it to lint all or individual PRDs, enforce stricter checks in continuous integration, fix common structural issues, or run only the reasoning pass.
Why use it?
It catches planning problems before implementation starts, when they are cheaper to correct.

Command for Claude Code

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 commands/samibs/skillfoundry/prd-lint
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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-lint

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/prd-lint.svg)](https://agentmods.dev/commands/samibs/skillfoundry/prd-lint)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/prd-lint"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/prd-lint.svg" alt="Measured on agentmods" height="20"></a>
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 1,934 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 $0.01934
Opus 5 $0.00000 $0.00967
Sonnet 5 $0.00000 $0.00387
Haiku 4.5 $0.00000 $0.00193

Measured yesterday against content hash 6f1bd96847b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-lint 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.

.claude/commands/prd-lint.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prd-lint — PRD Linter

Validates a PRD before /go or /forge runs on it — structural checks (template) and a semantic reasoning pass that catches requirement contradictions and gaps before a line of code exists.


Usage

/prd-lint                     Lint all PRDs in genesis/
/prd-lint <file>              Lint a specific PRD file
/prd-lint --strict <file>     Fail on warnings too (CI mode)
/prd-lint --fix <file>        Auto-fix common issues (add missing sections as stubs)
/prd-lint --reason <file>     Semantic pass only: reason over content for contradictions + gaps

A full lint runs two phases: structural checks (the scripts/prd-lint.sh script) then the semantic consistency pass below. Structure is necessary but not sufficient — a PRD can be perfectly formatted and still tell the pipeline to build two things that can't both be true.


Instructions

You are the PRD Linter. When invoked, run structural validation on PRD files in genesis/ to catch issues before they enter the implementation pipeline.

When invoked with no arguments:

Run bash scripts/prd-lint.sh genesis/ and report results.

When invoked with a file:

Run bash scripts/prd-lint.sh <file> and report results.

When invoked with --strict:

Run bash scripts/prd-lint.sh --strict <file> — treats warnings as errors. Use in CI or pre-/go gates.

When invoked with --fix:

After running the linter, auto-fix issues you can address without user input:

  • Add missing required sections as stubs (e.g., ## 8. Regression Surface with empty table)
  • Add FR-IDs column to user story tables if missing
  • Add - [ ] No new CRITICAL GuardLoop patterns detected to Definition of Done if missing
  • Do not fill in content that requires user knowledge (problem statement, constraints, etc.)

What the Linter Checks

Check Level Description
Front matter starts file ERROR File must open with --- on line 1
Required front matter fields ERROR prd_id, title, status, created, author
layers: not empty ERROR Must declare: [database, backend, frontend]
Required sections present ERROR §1–§5, §7–§11 must all exist
No TBD/TODO markers ERROR Outside comment blocks — blocks /go
status: DRAFT WARN Confirm PRD is ready
Vague language WARN might/maybe/possibly/somehow
Unchecked checkboxes [ ] WARN Unverified dependency versions
§6 Contract not empty WARN If present, must have content or Skip reason
§8 Regression Surface rows WARN Must list at least one feature at risk
§11.1 GuardLoop DoD item WARN Missing /guardloop scan clean check
§2 FR-IDs column WARN User story table missing traceability column

Read the full file on GitHub · 170 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. yesterday First seen · 170 lines · 0 tokens per session scan A 6f1bd96847b7

Subscribe to this mod's changes

prd-lint is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,934 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 2026-09-03.