prd-v03-features-value-planning

prd-v03-features-value-planning is a skill for Claude Code from mattgierhart/PRD-driven-context-engineering. It costs 150 tokens per session (2,153 once invoked), scanned A, original, MIT.

A product-planning method for deciding which features to build and why each one belongs in the product. A PRD is a product requirements document, and an MVP is the smallest useful first version.

In plain words
What is it for?
Use it to define and prioritize features, compare required features with differentiators, decide what belongs in the MVP, and map features to pricing tiers.
Why use it?
It prevents features from being added without a clear connection to user needs, success measures, competitive position, or pricing. It also makes the MVP scope explicit.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to define and prioritize features, compare required features with differentiators, decide what belongs in the MVP, and map features to pricing tiers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning
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.

Any agent
npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v03-features-value-planning
Clone the repo
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering

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-v03-features-value-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning/github.svg)](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v03-features-value-planning)
Your own site
<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.

agentmods 80×15 button for prd-v03-features-value-planning

Your own site · 80×15
<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>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,153 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00150 $0.02153
Opus 5 $0.00075 $0.01077
Sonnet 5 $0.00030 $0.00431
Haiku 4.5 $0.00015 $0.00215

Measured 9d ago against content hash 80e84bdb58a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/skills/prd-v03-features-value-planning/SKILL.md · 180 lines

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

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)

Read the full file on GitHub · 180 lines

Files

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.

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. 9d ago First seen · 180 lines · 150 tokens per session scan A 80e84bdb58a7

Subscribe to this mod's changes

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.