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 swan-gtm/gtm-skills --skill launch-window-mechanicsgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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/swan-gtm/gtm-skills/launch-window-mechanics)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/launch-window-mechanics"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/launch-window-mechanics/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/swan-gtm/gtm-skills/launch-window-mechanics"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/launch-window-mechanics.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 | $0.00172 | $0.02322 |
| Opus 5 | $0.00086 | $0.01161 |
| Sonnet 5 | $0.00034 | $0.00464 |
| Haiku 4.5 | $0.00017 | $0.00232 |
Grade A, and why
launch-window-mechanics 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Window Mechanics
Feeds do not distribute a post. They test it. A small slice of the audience sees it first, the system scores the reaction over the following half hour, and distribution either widens or stops. Almost everything written about creator marketing ends at publish. The reach was decided after that.
The job in this window is narrow: produce enough real, fast, high-quality reaction inside the test to clear the threshold, then decide whether the result deserves paid spend behind it.
Produces: a pre-publish setup, a timed sequence from thirty minutes before to two hours after, a go/no-go call on amplification with stop conditions, and a debrief that feeds the next cycle.
Before the post exists
The window cannot be worked if the post was not built to be worked. Three things are decided at draft time, not at publish time.
The post must create an obligation to respond. A neutral summary earns scrolling. A stated position, an open question, or a claim someone would want to correct earns replies, and replies are what the ranker weighs. This is not a call for provocation. It is the difference between "here is what we shipped" and "most teams are still doing this the slow way, here is the number that changed our mind."
Rights and attribution are contractual, not operational. The creator agreement must grant paid usage rights on the post itself, with a stated window. Without that clause, the post you spend six hours validating cannot be amplified, and renegotiating mid-window costs both time and leverage. This is the most common preventable failure in the sequence. Attribution goes in at the same time: a distinct tracking parameter or code per creator, and where links are not permitted, a read on branded-search lift instead.
The traffic needs somewhere to land. Reach is the entry, retention is the business. A spike arriving at a page with no next step is a spike that churns. Decide the destination before creating the demand: a signup path, a template, a resource, a community.
What ships with it
5 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.
- 9d ago First seen · 134 lines · 172 tokens per session scan A 05089be6d3b4
launch-window-mechanics is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 172 tokens to every session and 2,322 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
analytics
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…