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-v03-features-value-planninggit 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-v03-features-value-planning)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning/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-v03-features-value-planning"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning.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 | $0.00150 | $0.02153 |
| Opus 5 | $0.00075 | $0.01077 |
| Sonnet 5 | $0.00030 | $0.00431 |
| Haiku 4.5 | $0.00015 | $0.00215 |
Grade A, and why
prd-v03-features-value-planning 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Value Planning
Position in workflow: v0.3 Commercial Model → v0.3 Feature Value Planning → v0.4 User Journeys
Features are the unit of scope. Every feature must trace back to why it exists: outcome, moat, competitive position, or pricing tier.
Consumes
This skill requires prior work from v0.1-v0.3:
- CFD-* entries (customer feedback, from v0.1-v0.2) — Evidence for what users need/want
- KPI-* entries (outcome definitions, from v0.3 Outcome Definition) — What metrics does each feature support
- BR-* moat entries (from v0.3 Moat Definition) — What features defend our competitive position
- BR-* pricing entries (from v0.3 Pricing Model) — What features differentiate tiers
- Market landscape analysis (from v0.2) — Competitive feature comparison
This skill assumes v0.1-v0.2 research is complete and risk/tech decisions (v0.5) are not yet made.
Produces
This skill creates/updates:
- FEA-* entries (feature definitions, with confidence scoring) — Every feature in scope with traceability
- BR-FEA-* entries (governance rules for feature decisions) — Scope protection rules
- MVP-SCOPE artifact — Explicit list: "These X features (FEA-001, FEA-005, FEA-008) define our MVP"
- Example:
MVP-SCOPE: 5 P0 features + 3 P1 features = 8 total. Rationale: Delivers value on [KPI-001, KPI-002]. Competitive parity [FEA-001-003], Delta [FEA-004], Pricing [FEA-005] - This becomes the definition for v0.4 user journeys and v0.7 build scope
- Example:
All FEA- entries include confidence:
confidence: 2-3/5(based on CFD- evidence strength)- Evidence: "CFD-001, CFD-005, competitive-analysis"
- Forward target: "Would move to 4/5 if beta cohort uses it"
Feature Classification Framework
| Type | Definition | Strategic Purpose | Evidence Required |
|---|---|---|---|
| Moat | Builds/defends competitive advantage | Supports BR- moat rule | High (CFD- proving differentiation) |
| Outcome | Directly drives success metric | Tied to KPI- entry | High (KPI- link mandatory) |
| Parity | Matches competitor baseline | From Competitive Landscape | Medium (CFD- competitor evidence) |
| Delta | Differentiation from competitors | Our advantage over market | High (CFD- gap evidence) |
| Tier | Differentiates pricing packages | From Pricing BR- | Medium (BR- tier assignment) |
| Table Stakes | Expected but not differentiating | Industry standard | Low (common knowledge) |
What ships with it
3 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 · 180 lines · 150 tokens per session scan A 80e84bdb58a7
prd-v03-features-value-planning is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 150 tokens to every session and 2,153 once invoked, about $0.0007 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.