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 skills add gokulrajaram/ProductSpec --skill productspec-authoringgit clone --depth 1 https://github.com/gokulrajaram/ProductSpecWrote 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/gokulrajaram/productspec/productspec-authoring)<a href="https://agentmods.dev/skills/gokulrajaram/productspec/productspec-authoring"><img src="https://agentmods.dev/badge/skills/gokulrajaram/productspec/productspec-authoring/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.
<a href="https://agentmods.dev/skills/gokulrajaram/productspec/productspec-authoring"><img src="https://agentmods.dev/badge/skills/gokulrajaram/productspec/productspec-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00090 | $0.00839 |
| Opus 5 | $0.00045 | $0.00419 |
| Sonnet 5 | $0.00018 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
productspec-authoring 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 11d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring ProductSpec Files
ProductSpec is a Markdown format for the product decision that comes before tickets, engineering plans, and code. One file per feature holds the committed intent.
This skill covers producing that file. Reading a finished spec and building against it is a different job, and the productspec skill covers it. This skill ends when the file validates.
Always true
- Files use the extension
.product-spec.md: YAML frontmatter between---markers, then## Sectionheadings. - Six sections are mandatory, in order:
problem,hypothesis,product_summary,scope,acceptance_criteria,success_metrics. - Headings match case- and separator-insensitively.
## Acceptance Criteriaand## acceptance_criteriaare the same section. Title case is the convention. - Frontmatter requires
spec_format_version: "0.1",title,artifact_type(hypothesis|prd|openspec_proposal),author,created_at,updated_at. Optional:spec_revision,linked_github_repo,applies_to,custom_sections,tool_metadata. acceptance_criteriaandsuccess_metricseach carry a required fenced block. Prose alone fails validation. Structured scope, AI evals, and related artifacts are optional.- Structured items carry durable ids:
AC-<number>,SM-<number>,EVAL-<number>. Other documents cite them. - AI evals live inside
## Acceptance Criteria, never in a section of their own. Related artifacts live inside## Related Artifacts. - Validate any file with:
npm exec --yes --package @productspec/parser -- productspec validate <file>(--yessuppresses npm's interactive install prompt, which hangs CI and non-interactive agents). - The full normative definition is SPEC.md in the ProductSpec repository: https://github.com/gokulrajaram/ProductSpec/blob/main/SPEC.md. When this skill and SPEC.md disagree, SPEC.md wins.
Pick the task, read one reference
| Task | Read |
|---|---|
| Write a new spec from scratch | references/authoring.md |
| Validate files and fix errors | references/validating.md |
| Convert an existing PRD or feature doc | references/converting.md |
| Record drift, revisions, and outcomes | references/decision-trace.md |
What ships with it
4 files 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.
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.
- 11d ago First seen · 45 lines · 90 tokens per session scan A 25fb8a41d19f
productspec-authoring is a skill published in the GitHub repository gokulrajaram/ProductSpec (286 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 839 once invoked, about $0.0005 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
product-principles
Defines 4 Risks confidence thresholds, OST hierarchy levels, Knowledge Pyramid tiers, and state design requirements. Use when evaluating user stories, setting confidence scores, referencing OST levels, scoping MVP, or determining validation sufficiency.
hypothesis-discipline
Manages hypothesis lifecycle, enforces validation criteria, time budgets, and confidence scoring rules. Use when creating hypotheses, updating confidence scores, setting validation criteria, handling timeouts, or recording validation results.
blueprint-standards
Defines structural design artifact formats — information architecture, user flows, content model, brand direction, Visual Tokens, and AI interaction model. Use when creating or reviewing design artifacts that precede prototype generation.
recipe-validate
Validates a hypothesis with a risk-appropriate method and records decision-relevant evidence. Use when testing Value, Usability, Feasibility, or Viability assumptions.
recipe-define
Creates a delivery-ready PRD from validated hypotheses with material 4 Risks evidence and necessary traceability. Use when turning validation results into requirements or user stories.
recipe-discover
Frames product Opportunities and creates decision-relevant hypotheses from available evidence. Use when exploring a problem, market opportunity, or user need.