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-moat-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-moat-definition)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v03-moat-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-moat-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-moat-definition"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v03-moat-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 | $0.00126 | $0.02134 |
| Opus 5 | $0.00063 | $0.01067 |
| Sonnet 5 | $0.00025 | $0.00427 |
| Haiku 4.5 | $0.00013 | $0.00213 |
Grade A, and why
prd-v03-moat-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 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moat Definition
Position in HORIZON workflow: v0.2 Competitive Landscape → v0.3 Moat Definition → v0.3 Pricing Model Selection
Consumes
This skill requires prior work from v0.2:
- Landscape map artifact (from Competitive Landscape Mapping) — Current behavior documentation, feature matrix, competitor analysis
- CFD-* entries (competitive intelligence, from Competitive Landscape Mapping) — Documented competitors with pricing, features, user feedback
- BR-* product type entry (from Product Type Classification) — Classification constrains which competitors are relevant to analyze
This skill assumes v0.2 analysis is complete with documented competitors.
Produces
This skill creates/updates:
- CFD-* entries (competitor moat analysis) — Assessment of each competitor's defensibility by moat type
- BR-* entries (targeting rules) — Constraints derived from moat analysis, defining where to compete vs. avoid
- Moat strength inventory artifact — Summary of competitor moats with vulnerability signals
All CFD moat analysis entries should include:
confidence: 2-3/5(based on public evidence + user interviews about switching friction)- Evidence source (pricing pages, reviews, customer interviews)
- Forward target: "Would move to 4/5 if we interview 5+ current/former customers about switching costs"
Example moat analysis entry:
CFD-055: Competitor Moat Analysis — Notion
Competitor: Notion
Primary Moat Type: Switching Costs (data lock-in)
Moat Strength Tier: Strong
Confidence: 3/5 (source: public-research + 2-user-interviews)
Date: 2026-02-01
Switching Cost Quantification:
- Financial: Multi-year contract, no early termination ($0 direct cost)
- Time/Effort: 20+ hours migration, team retraining
- Data Migration: Proprietary database format (complex export)
- Workflow Retraining: Unique templates, team habits
- Integration Rework: Deep Slack/GitHub dependencies
Total Switching Cost: $3K in labor + 20 hours = Material friction
Moat Verdict: Strong — switching costs >$3K + meaningful time investment
Vulnerability Signal: SMB segment with small teams; they use <20% of feature set (opportunity for simpler tool)
Targeting Decision: Avoid direct competition. Wedge in SMB with simplified, cheaper offering.
Evidence:
- CFD-042 (landscape): Reviews show enterprise love; SMB complaints focus on cost + complexity
- CFD-015 (value hypothesis): SMB would save $12,500/year with simpler tool
Next Target: "Would move to 4/5 if we interview 5+ SMB teams about exact switching cost dollars"
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 · 206 lines · 126 tokens per session scan A 8023b705dd23
prd-v03-moat-definition is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 126 tokens to every session and 2,134 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.