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-v10-continuous-discovery-torresgit 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-v10-continuous-discovery-torres)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-continuous-discovery-torres"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-continuous-discovery-torres/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-v10-continuous-discovery-torres"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-continuous-discovery-torres.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 | $0.00116 | $0.02760 |
| Opus 5 | $0.00058 | $0.01380 |
| Sonnet 5 | $0.00023 | $0.00552 |
| Haiku 4.5 | $0.00012 | $0.00276 |
Grade A, and why
prd-v10-continuous-discovery-torres 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Discovery (Torres)
Position in workflow: v1.0 Crossing the Chasm (Moore) → v1.0 Continuous Discovery (Torres) → v1.0 Mom Test, Case Study Builder
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | One outcome + 3–5 opportunities + interview cadence proposal |
| standard | Full Opportunity Solution Tree (outcome → opportunities → solutions → assumption tests); weekly 3-interview cadence; assumption-mapping for top solution |
| deep | Multi-outcome tree; per-opportunity confidence scoring; full assumption tests with experiment plans; cross-discipline trio (PM/design/eng) participation rules |
What This Does
Establishes continuous discovery as a weekly habit, not a one-time research phase. The shift from "we do research before building" to "we talk to customers every week" is what separates teams that find PMF from teams that drift.
The work product is the Opportunity Solution Tree — a structured artifact that connects a measurable business outcome to opportunities (customer needs), to candidate solutions, to assumption tests. The tree is living: it grows and prunes as interviews accumulate.
This skill assumes prd-v10-mom-test-interview is the discipline for how to interview; this skill is the discipline for what to do with the interviews.
How It Works
- Define one measurable outcome — Not an output ("ship feature X"), but an outcome ("activated users in beachhead segment grow 20% MoM"). Anchor in ADO-STAGE-* and KPI-*.
- Set up weekly cadence — 3+ customer interviews per week, ongoing. Not "until we feel done." Continuous.
- Map opportunities under the outcome — Each opportunity is a customer pain or need (not a feature). Phrased in customer words. Grouped under the outcome. Sourced from interviews.
- Pick top opportunity — Score by outcome-impact × evidence-strength × addressability. Focus on one at a time.
- Brainstorm solutions — Multiple candidate solutions per opportunity. Not "the obvious one." Force divergent options.
- Assumption-map the top solution — What must be true for this solution to work? Three categories: desirability (do they want it?), viability (will it grow our outcome?), feasibility (can we build it?).
- Test the riskiest assumption first — Smallest experiment that disproves the assumption if it's wrong. Update tree.
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 · 224 lines · 116 tokens per session scan A b964c05da753
prd-v10-continuous-discovery-torres is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 116 tokens to every session and 2,760 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.