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-channels-orbgit 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-channels-orb)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-channels-orb"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-channels-orb/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-channels-orb"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v09-launch-channels-orb.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 | $0.00115 | $0.02830 |
| Opus 5 | $0.00057 | $0.01415 |
| Sonnet 5 | $0.00023 | $0.00566 |
| Haiku 4.5 | $0.00012 | $0.00283 |
Grade A, and why
prd-v09-launch-channels-orb 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Channels (ORB: Owned / Rented / Borrowed)
Position in workflow: v0.9 Offer Construction (Hormozi) → v0.9 Launch Channels (ORB) → 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 | 1 channel per layer (3 channels total); single-week sequence |
| standard | 2–3 channels per layer; pre-launch / launch / post-launch sequence; attribution plan per channel |
| deep | Full portfolio; per-channel content strategy; budget allocation; per-channel ROI projection; channel-mix risk register |
Framework: Owned / Rented / Borrowed (ORB)
ORB classifies every distribution channel by who controls the audience. The rule: own the relationship, rent the platform, borrow the reach — and balance the portfolio so no single channel can take you out.
| Layer | Definition | Examples | Cost | Compounding |
|---|---|---|---|---|
| Owned | You control the audience and the channel | Email list, website, product itself, blog you host, customer base | Time + tools | High — every additional list member compounds future launches |
| Rented | You build presence on someone else's platform | Twitter/X, LinkedIn, YouTube, Slack/Discord communities, podcasts you host | Time | Medium — platform changes rules; audience is portable but messy |
| Borrowed | You access someone else's audience temporarily | Press, podcast guesting, influencers, paid acquisition, integrations, partnerships, affiliate | Money or favor | Low — one-time reach unless converted to Owned/Rented |
The Channel Allocation Principles
- Build Owned before launch, rent through launch, borrow at launch. Without an owned audience, the launch is a one-shot dependent on borrowed reach.
- Pick channels your best-fit segment already uses. Pulled from the Positioning best-fit characteristics — not from "what's popular this quarter."
- One channel per layer to start. Too many channels at once = no signal which is working. Add channels by tier 2–3 only once tier-1 attribution is clean.
- Convert Borrowed → Owned aggressively. Every press hit, podcast guest spot, or partnership should funnel to an owned channel (email signup, demo request) — otherwise it's vanity reach.
- Borrowed scales reach; Owned scales repeat. A launch is a moment; the goal is a list.
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 · 241 lines · 115 tokens per session scan A 2045c19cf56a
prd-v09-launch-channels-orb is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 9d ago), licensed MIT. It adds 115 tokens to every session and 2,830 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.