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-chasm-adoption-mooregit 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-chasm-adoption-moore)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-chasm-adoption-moore"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-chasm-adoption-moore/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-chasm-adoption-moore"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-chasm-adoption-moore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 187 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00149 | $0.03166 |
| Opus 5 | $0.00075 | $0.01583 |
| Sonnet 5 | $0.00030 | $0.00633 |
| Haiku 4.5 | $0.00015 | $0.00317 |
Grade A, and why
prd-v10-chasm-adoption-moore 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crossing the Chasm (Moore) — the v1.0 Spine
Position in workflow: v0.9 Feedback Loop Setup → v1.0 Crossing the Chasm (Moore) → all v1.0 work
Execution Mode
Default is deep (this is a major strategic decision; quick mode is for hypothesis pre-work only). See .claude/rules/08-skill-execution-modes.md.
| Mode | What this skill produces |
|---|---|
| quick | Stage assessment only (ADO-STAGE-*); beachhead candidate hypothesis |
| standard | Stage assessment + beachhead segment + top 3 whole-product gaps + reference-account candidate list |
| deep (default) | Full stage assessment with evidence + sharpened beachhead with in/not-in criteria + complete whole-product gap analysis + reference-account cultivation plan + chasm-crossing risk register |
Framework: Moore's Technology Adoption Lifecycle
From Crossing the Chasm (Geoffrey Moore, 1991, updated 2014). The bestselling tech-strategy book of the 1990s, and still the canonical model for understanding why early traction doesn't predict mass adoption.
The lifecycle
| Stage | % of market | Buyer mindset | What they buy |
|---|---|---|---|
| Innovators (2.5%) | Tinkerers; technology enthusiasts | Want to try new things; tolerate incomplete products | Vision, technical depth, access |
| Early Adopters (13.5%) | Visionaries | Want strategic advantage from non-mainstream tech | Bold vision + first-mover ROI |
| — THE CHASM — | — | — | — |
| Early Majority (34%) | Pragmatists | Want reliable productivity gains from proven solutions | Whole product + segment-specific references |
| Late Majority (34%) | Conservatives | Want safe, mature defaults | Market leadership, low risk |
| Laggards (16%) | Skeptics | Resist change | (Generally not worth targeting) |
The chasm
The gap between Early Adopters and Early Majority is the chasm. Most products die here. The reason: visionary buyers (who got you to early traction) actively want the cutting-edge, while pragmatist buyers want to be the second penguin off the iceberg — they need to see peers in their segment succeeding first.
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 · 218 lines · 149 tokens per session scan A b1d009a35ed2
prd-v10-chasm-adoption-moore is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 149 tokens to every session and 3,166 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.