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-v04-persona-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-v04-persona-definition)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v04-persona-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v04-persona-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-v04-persona-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v04-persona-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 | $0.00139 | $0.02369 |
| Opus 5 | $0.00069 | $0.01184 |
| Sonnet 5 | $0.00028 | $0.00474 |
| Haiku 4.5 | $0.00014 | $0.00237 |
Grade A, and why
prd-v04-persona-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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona Definition
Position in workflow: v0.3 Feature Value Planning → v0.4 Persona Definition → v0.4 User Journey Mapping
Personas are not demographic profiles—they are behavioral models synthesized from evidence. Every persona must trace back to CFD- research, BR- targeting rules, and FEA- features they care about.
Consumes
This skill requires prior work from v0.1-v0.3:
- CFD-* problem statements and pain points (from v0.1 Problem Framing) — Behavioral signals about what users struggle with
- CFD-* value hypotheses (from v0.1 User Value Articulation) — Evidence about what users want to accomplish
- CFD-* competitive intelligence and segment gaps (from v0.2 Competitive Landscape) — Market segmentation and underserved signals
- BR-* targeting rules (from v0.3 Moat Definition) — Constraints on which segments to pursue (switchers vs. new-to-category, etc.)
- BR-* product type classification (from v0.2 Product Type Classification) — Determines which personas matter (Clone = feature parity users; Undercut = price-sensitive niche)
- FEA-* entries (from v0.3 Features Value Planning) — Feature list to validate which features each persona cares about
- MVP-SCOPE artifact (from v0.3 Features Value Planning) — The explicit list of features defining MVP; personas map to MVP feature set only
This skill assumes v0.1-v0.3 work is complete.
Produces
This skill creates/updates:
- PER-* entries (persona definitions, confidence 2-3/5) — Behavioral profiles tied to CFD/BR/FEA evidence with acquisition channels and pricing sensitivity
- Persona coverage artifact — Map of which personas are Primary/Secondary and which product type segments they represent
All PER- entries should include:
confidence: 2-3/5(based on evidence tier from CFD interviews and BR targeting decisions)- Evidence source citations (CFD-ID references + BR-ID targeting rules)
- Forward target: "Would move to 4/5 if we validate persona behaviors with 5+ actual customers"
What ships with it
2 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 · 219 lines · 139 tokens per session scan A b9e6ef6c18bf
prd-v04-persona-definition is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 11d ago), licensed MIT. It adds 139 tokens to every session and 2,369 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.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…