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-v09-launch-metricsgit 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-v09-launch-metrics)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-metrics"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-metrics/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-v09-launch-metrics"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-metrics.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 | $0.00081 | $0.04905 |
| Opus 5 | $0.00041 | $0.02452 |
| Sonnet 5 | $0.00016 | $0.00981 |
| Haiku 4.5 | $0.00008 | $0.00490 |
Grade A, and why
prd-v09-launch-metrics 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Metrics
Position in workflow: v0.9 GTM Strategy → v0.9 Launch Metrics → v0.9 Feedback Loop Setup
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | 3 KPIs (one each for Reach/Acquisition/Activation); Day 7 targets; basic dashboard |
| standard | Full funnel (Reach → Referral); Day 1/7/30 targets; dashboards + alerts |
| deep | Full funnel + tier targets + Day 1/7/30/90 + product-type calibration + cohort analysis |
Consumes
This skill requires prior work from v0.3-v0.9:
- KPI-* outcome entries from v0.3 (from v0.3 Outcome Definition) — Baseline KPI- entries define success metrics for the product; launch-specific KPI- entries are calibrated variants
- GTM-* campaign specifications (from v0.9 GTM Strategy) — GTM channels inform launch-specific KPI- tracking (e.g., Product Hunt channel → KPI for PH-originated signups); timeline defines metric collection windows (Day 1, Day 7, Day 30, Day 90)
- BR-* product type (from v0.2 Product Type Classification) — Product type (Clone/Unbundle/Undercut/Slice/Innovation) determines metric targets and benchmarks (Fast Follow = higher activation expected, lower retention)
- CFD-* market benchmarks (from v0.1-v0.2 research) — Competitive analysis and market data inform realistic KPI- targets (e.g., "developer tools average 30-50% activation")
- DEP-* deployment infrastructure (from v0.8 Release Planning) — Deployment baselines from staging inform KPI- thresholds (e.g., error rate baseline → activation threshold)
- MON-* monitoring setup (from v0.8 Monitoring Setup) — Infrastructure metrics (latency, error rate) inform KPI- dashboards and alert conditions during launch
This skill assumes GTM- entries are complete and tracking infrastructure is configured.
Produces
This skill creates/updates:
What ships with it
4 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 · 539 lines · 81 tokens per session scan A e6c8e2734cb5
prd-v09-launch-metrics is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 81 tokens to every session and 4,905 once invoked, about $0.0004 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…