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 skills/samibs/skillfoundry/prd-lintnpx skills add samibs/skillfoundry --skill prd-lintgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/skills/samibs/skillfoundry/prd-lint)<a href="https://agentmods.dev/skills/samibs/skillfoundry/prd-lint"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/prd-lint.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 | $0.00013 | $0.01958 |
| Opus 5 | $0.00006 | $0.00979 |
| Sonnet 5 | $0.00003 | $0.00392 |
| Haiku 4.5 | $0.00001 | $0.00196 |
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 3d 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 — 176 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 Surfacewith empty table) - Add
FR-IDscolumn to user story tables if missing - Add
- [ ] No new CRITICAL GuardLoop patterns detectedto 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 |
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.
- 3d ago First seen · 176 lines · 13 tokens per session scan A dce9549a5af6
prd-lint is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,958 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
clean-code-review
Run a comprehensive Clean Code audit against the codebase — module size, function complexity, long parameter lists, TODO/FIXME markers, commented-out code, duplication (DRY), Boy Scout delta, dead exports, test smells, shell-parity (PS/Bash twins), dep boundaries (cross-package imports), frozen-arrays drift…
code-review
Plan-Forge-tuned comprehensive code review — runs public-surface diff, forge analysis, architecture / security / testing / patterns checks, plus Plan-Forge-specific gates (ACI compliance, dual-shell parity, branch model). Use before merging features or at the end of a phase. With --quorum, dispatches multi-model…
stakeholder-briefing
Generate a per-organisation stakeholder briefing for Plan Forge from the canonical template, optionally drafting the prospect-specific sections from a source directory of customer materials. Use when an internal champion needs to walk a colleague or VP through the decision to adopt Plan Forge.
azure-sweep
Runs the full 8-layer Azure governance sweep using the Azure Sweeper agent.
bug-fix
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.
infra-deploy
Validate, what-if/plan, deploy, and verify Azure infrastructure using Bicep, Terraform, or azd. Use when deploying a completed infrastructure phase to an environment.