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-outcome-definitiongit 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-outcome-definition)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v03-outcome-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-outcome-definition/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-outcome-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-outcome-definition.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 | $0.00123 | $0.01907 |
| Opus 5 | $0.00062 | $0.00954 |
| Sonnet 5 | $0.00025 | $0.00381 |
| Haiku 4.5 | $0.00012 | $0.00191 |
Grade A, and why
prd-v03-outcome-definition 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome Definition
Position in HORIZON workflow: v0.2 Product Type Classification → v0.3 Outcome Definition → v0.3 Pricing Model Selection
Consumes
This skill requires prior work from v0.2:
- BR-* product type entry (from Product Type Classification) — Classification determines which metrics are relevant
- CFD-* entries (from Problem Framing and Competitive Landscape) — Customer evidence about desired outcomes
- Market benchmarks and competitor metrics — Reference data for Tier 1/2 targets
This skill assumes v0.2 classification is complete.
Produces
This skill creates/updates:
- KPI-* entries (outcome definitions) — Measurable success metrics tied to product type
- BR-* outcome rules (optional) — Constraints derived from KPI thresholds (e.g., "Launch blocked if LTV:CAC < 3:1")
- Success criteria artifact — Dashboard of leading + lagging indicators that define product-market fit
All KPI entries should include:
confidence: 2-3/5(based on benchmark evidence, not just assumptions)- Evidence source (competitor benchmarks, CFD validation, industry reports)
- Forward target: "Would move to 4/5 if we observe real customer data"
Example KPI entry with confidence:
KPI-001: Time to First Revenue
Type: Tier 1 (Revenue)
Category: Lagging
Definition: Days from market signal identification to first paying customer
Target: ≤14 days
Confidence: 2/5 (source: GearHeart-methodology + 0-customer-validation)
Evidence: BR-001 (GearHeart standard); No pre-customer validation yet
Next Target: "Would move to 4/5 if actual customer reaches paying status in ≤14 days"
Downstream Gate: v0.5 Red Team — if not hit by Day 21, evaluate pivot
---
KPI-002: Conversion Rate (Trial → Paid)
Type: Tier 2 (Leading Indicator)
Category: Leading
Definition: (Paid customers / Trial signups) × 100, measured over 60-day trial period
Target: ≥15% (benchmark: SaaS median 10-15%)
Confidence: 3/5 (source: SaaS-benchmarks + 1-SMB-validation-conversation)
Evidence: CFD-042 (competitive landscape shows SMB conversion patterns)
Next Target: "Would move to 4/5 if we see actual cohort conversion in our product"
Downstream Gate: v0.7 Build Execution — EPIC complete when KPI-002 validated
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.
- 11d ago First seen · 177 lines · 123 tokens per session scan A d5cc2f946397
prd-v03-outcome-definition is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 123 tokens to every session and 1,907 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.