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-cold-outreach-tieredgit 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-cold-outreach-tiered)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v09-cold-outreach-tiered"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-cold-outreach-tiered/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-cold-outreach-tiered"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-cold-outreach-tiered.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 | $0.00111 | $0.02694 |
| Opus 5 | $0.00056 | $0.01347 |
| Sonnet 5 | $0.00022 | $0.00539 |
| Haiku 4.5 | $0.00011 | $0.00269 |
Grade A, and why
prd-v09-cold-outreach-tiered 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 12d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Outreach (Tiered: 1:1 / 1:few / 1:many)
Position in workflow: v0.9 Offer Construction → v0.9 Cold Outreach (Tiered) → v0.9 Launch Metrics
Execution Mode
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | One tier (typically Tier 2); 3-touch sequence; lead-list scoring rubric |
| standard | All three tiers; 3–5 touches each; lead-list scoring + tier-assignment logic; reply-handling guide |
| deep | All tiers + A/B subject lines per tier; channel mix (email + LinkedIn + voicemail); reply-rate baselines; objection library |
What This Does
Builds three differentiated cold-outreach sequences, each calibrated to a different ratio of research-per-lead:
- Tier 1 (1:1, founder-led) — Hand-researched. Highly personalized. Each touch references something specific. Volume: 10–30 contacts.
- Tier 2 (1:few, semi-automated) — Segment-personalized. Template with 3–5 dynamic variables per recipient. Volume: 100–500 contacts.
- Tier 3 (1:many, automated) — Broad-fit. Template only, minimal personalization. Volume: 1,000–10,000+ contacts.
The tiers are not "good/better/best" — each has its place. Tier 3 fills the top of the funnel cheaply. Tier 2 carries the bulk. Tier 1 closes the highest-value targets that templates can never reach.
How It Works
- Source lead lists from ICP — Pull from the Positioning best-fit characteristics. Use enrichment tools (Apollo, Clay, Clearbit) or LinkedIn Sales Nav search anchored on firmographic + behavioral signals from PER-.
- Score each lead's signal strength (1–5):
- Trigger signal — Recent funding, hiring, product launch, public pain (5)
- Fit signal — Strong firmographic/behavioral match without specific trigger (3–4)
- Cold signal — Broad-fit only; no specific signal (1–2)
- Tier assignment:
- Signal 4–5 + opportunity size ≥ threshold → Tier 1
- Signal 3–4 → Tier 2
- Signal 1–2 → Tier 3 (or drop if list is large enough)
- Build per-tier sequences — Each tier gets its own template structure (see Output Template). Tier 1 is hand-drafted; Tier 2 is template + variables; Tier 3 is template only.
- End every sequence on the guarantee — The guarantee from prd-v09-offer-construction-hormozi is the reply-friction killer. Don't ask for a meeting cold; ask them to invoke the guarantee.
- Plan reply handling — Define what counts as a reply (positive, ask, objection, unsubscribe), and have a response cadence for each. Tier 1 replies go to founder immediately. Tier 3 replies route through a templatized objection library.
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.
- 12d ago First seen · 209 lines · 111 tokens per session scan A 9775edaadff1
prd-v09-cold-outreach-tiered is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 11d ago), licensed MIT. It adds 111 tokens to every session and 2,694 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…