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-v05-risk-discovery-interviewgit 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-v05-risk-discovery-interview)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v05-risk-discovery-interview"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v05-risk-discovery-interview/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-v05-risk-discovery-interview"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v05-risk-discovery-interview.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 | $0.00134 | $0.03219 |
| Opus 5 | $0.00067 | $0.01610 |
| Sonnet 5 | $0.00027 | $0.00644 |
| Haiku 4.5 | $0.00013 | $0.00322 |
Grade A, and why
prd-v05-risk-discovery-interview 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 10d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Discovery Interview
Position in workflow: v0.4 Screen Flow Definition → v0.5 Risk Discovery Interview → v0.5 Technical Stack Selection
This is an interactive interview skill. The AI asks questions, the user reflects and decides. The goal is to surface risks so the user can mitigate or accept them—not to kill ideas.
Consumes
This skill requires prior work from v0.1-v0.4:
- CFD-* all customer feedback entries (from v0.1-v0.2) — User research foundation; reveals confidence tier in market assumptions
- BR-* all business rules (from v0.2-v0.3) — Constraints on what can change (pricing, moat, product type constrain risk responses)
- FEA-* feature entries (from v0.3) — Feature complexity and priorities signal technical risks
- PER-* persona entries (from v0.4) — Persona distribution and behaviors reveal adoption risks and churn signals
- UJ-* journey entries (from v0.4) — Journey complexity signals friction points; long journeys increase adoption risk
- SCR-* screen entries (from v0.4) — Screen count and design complexity informs technical resource risk
This skill assumes v0.1-v0.4 work is complete and serves as context for interview discovery.
Produces
This skill creates/updates:
- RISK-* entries (risk discovery, owner-assigned severity) — Identified risks with Impact/Likelihood scoring (raw score from 1-9), response type (Mitigate/Accept/Avoid/Transfer), specific mitigations, and owners
- README Risk Scorecard — Baseline risk profile aggregated by category (Market/User/Technical) with total scores and risk level assessment
- Risk mitigation summary — Top 3-5 risks requiring active mitigation before v0.6 architecture work
All RISK- entries are created through user decision during the interview; they reflect explicit owner choices on severity, not AI assumptions:
Example RISK- entry (user-scored):
RISK-001: Market — Competitor Feature Parity
Description: Competitor X launches report scheduling feature (our FEA-003 planned) within 60 days
Trigger: Competitor announces roadmap; sees our landing page
Impact: High (3) — User severity assessment based on competitive urgency
Likelihood: Medium (2) — User assessment of competitor execution speed
Raw Score: 6 (3 × 2)
Status: open
Effective Score: 6.0
Early Signal: Competitor job postings for feature area, beta announcement
Response: Mitigate
Mitigation: Accelerate FEA-003 launch by 30 days; add scheduling as P0 (links to FEA-003, KPI-002)
Owner: Product Lead
Linked IDs: FEA-003 (report scheduling), KPI-002 (activation rate), BR-042 (undercut positioning)
Review Date: Weekly during v0.6 (architecture phase)
Added: v0.5
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.
- 10d ago First seen · 299 lines · 134 tokens per session scan A 12dbc3fe9f6c
prd-v05-risk-discovery-interview is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 134 tokens to every session and 3,219 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.