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 mattgierhart/PRD-driven-context-engineering --skill prd-v02-product-type-classificationgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v02-product-type-classification)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v02-product-type-classification"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v02-product-type-classification/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/mattgierhart/prd-driven-context-engineering/prd-v02-product-type-classification"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v02-product-type-classification.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 | $0.00121 | $0.01654 |
| Opus 5 | $0.00060 | $0.00827 |
| Sonnet 5 | $0.00024 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00165 |
Grade A, and why
prd-v02-product-type-classification 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 9d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Type Classification
Position in HORIZON workflow: v0.2 Competitive Landscape → v0.2 Product Type Classification → v0.3 Outcome Definition
Consumes
This skill requires prior work from v0.2:
- Landscape map artifact (from Competitive Landscape Mapping) — Current behavior documentation, feature matrix, competitor analysis
- CFD-* entries (competitive intelligence, from Competitive Landscape Mapping) — Evidence from 3+ direct competitors + adjacent solutions
- BR-* positioning rules (from Competitive Landscape Mapping) — Constraints derived from competitive analysis
This skill assumes v0.2 Competitive Landscape is complete with documented landscape analysis.
Produces
This skill creates/updates:
- BR-* entries (product type classification) — Decision record showing which of the six types this product is
- BR-* entries (GTM constraints inherited from type) — Pricing, channel, scope, and timeline implications of the chosen type
- Product type artifact — Named decision: "We are building a [Type] product because [specific evidence from landscape]"
Example product type classification entry:
BR-042: Product Type Classification
Type: Classification Decision
Date: 2026-02-01
Confidence: 70% (source: competitive-landscape-analysis + 3-customer-interviews)
Classification: UNDERCUT
Rationale: All 3 direct competitors (Notion, Linear, Figma) serve enterprise/mid-market first; SMB segment underserved. We can deliver 80% of feature set at 40% price for SMB-specific workflows.
Evidence:
- CFD-015 (landscape): "All competitors start at $50/user/month enterprise pricing"
- CFD-018 (landscape): "3 SMB teams using workarounds because pricing doesn't fit budget"
- CFD-001 (value hypothesis): "$12,500/year value for 5 core features only"
GTM Constraints (inherited):
- Pricing: Must be <$200/user/month to justify switching
- Channel: Direct sales to SMB, not marketplace/enterprise
- Scope: Ruthlessly cut features; 5 core + 3 differentiators max
- Timeline: Fast iteration with SMB feedback; can't outspend enterprise marketing
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.
- 9d ago First seen · 162 lines · 121 tokens per session scan A c4348b17e01f
prd-v02-product-type-classification is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 121 tokens to every session and 1,654 once invoked, about $0.0006 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.