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-v08-marketing-ops-handoffgit 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-v08-marketing-ops-handoff)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v08-marketing-ops-handoff"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-marketing-ops-handoff/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-v08-marketing-ops-handoff"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v08-marketing-ops-handoff.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 | $0.00119 | $0.02777 |
| Opus 5 | $0.00060 | $0.01388 |
| Sonnet 5 | $0.00024 | $0.00555 |
| Haiku 4.5 | $0.00012 | $0.00278 |
Grade A, and why
prd-v08-marketing-ops-handoff 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing-Ops Handoff (Lead Lifecycle + Sales Routing)
Position in workflow: v0.8 Monitoring Setup → v0.8 Marketing-Ops Handoff → v0.9 Launch Channels (ORB), v0.9 Cold Outreach
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | 3-stage lifecycle (Anonymous → Lead → Customer); single handoff rule; SLA per stage |
| standard | Full 5-stage lifecycle (Anonymous → MQL → SQL → Opportunity → Customer); entry/exit criteria; handoff payload spec; SLAs |
| deep | Full lifecycle + per-segment routing (by ICP / region / size); scoring model; rejection-loop rules; SLA monitoring + escalation |
What This Does
Defines the lifecycle stages a lead passes through from first touch to customer (or churn), plus the handoff rules at each transition. Without this, marketing-captured leads get dropped, double-worked, or never followed up. With this, you have an auditable definition of who owns what at each moment.
This skill applies primarily to B2B and prosumer products with a human-touch sales motion (founder-led sales, BDR/SDR teams, customer-success-led expansion). Pure self-serve products use a simpler version: lifecycle = Anonymous → Trial → Paid, with no human handoff.
How It Works
- Pick the lifecycle shape — Match the product:
- Self-serve: Anonymous → Signup → Activated → Paid → Expanded
- Sales-assisted: Anonymous → MQL → SQL → Opportunity → Customer
- Hybrid (PLG + Sales): Anonymous → Signup → Activated → Paid → SQL → Opportunity → Expansion
- Define entry criteria per stage — What event/behavior moves a lead into this stage? Examples:
- MQL: filled out a high-intent form, downloaded gated content, hit usage threshold
- SQL: explicit "talk to sales" or scoring threshold reached
- Opportunity: discovery call held, budget + authority confirmed
- Define exit criteria per stage — Two paths out: progress (to next stage) and disqualify (back to nurture or out). Disqualification rules matter as much as progression.
- Map ownership — Who owns the lead at each stage:
- Anonymous: marketing automation
- MQL: BDR/SDR
- SQL: AE / founder
- Opportunity: AE / founder
- Customer: CS / founder
- Define handoff payload — When a lead moves between owners, what context goes with them? At minimum:
- Source (which GTM-* channel produced this lead)
- Touchpoint history (what they've engaged with)
- Best-fit signals (firmographic match, behavioral fit)
- Disqualifiers (anything that ruled out an earlier stage)
- Open questions (what the next owner should clarify)
- Set SLAs per stage — How fast must the new owner respond after handoff? MQL → BDR typically <1 business hour for high-signal, <1 business day for low-signal. SQL → AE typically <30 minutes.
- Plan rejection routing — When SQL → AE handoff is rejected ("not a fit"), where does the lead go? Back to nurture, disqualified, requeued? Without this rule, leads die in limbo.
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 · 220 lines · 119 tokens per session scan A 276605bc47e0
prd-v08-marketing-ops-handoff is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 11d ago), licensed MIT. It adds 119 tokens to every session and 2,777 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.
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…