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 citation-gap-outreachgit 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/citation-gap-outreach)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/citation-gap-outreach"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/citation-gap-outreach/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/citation-gap-outreach"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/citation-gap-outreach.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 | $0.00090 | $0.00619 |
| Opus 5 | $0.00045 | $0.00309 |
| Sonnet 5 | $0.00018 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
citation-gap-outreach 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use when the sources feeding AI answers in a category are known and the brand needs to get into them. Produces a ranked get-listed plan with the right ask per source and a re-measure loop that proves each placement landed.
Rank by answers fed, not authority
Order target sources by how many category answers each one fed. Domain authority, traffic, and prestige all mislead here: a modest directory feeding nine answers outranks a famous publication feeding one. The citation count is the value of the placement; everything else is habit carried over from link building.
Match the ask to the source
Each source type gets updated a different way, and the ask must match it. A directory or listing site wants a submission or a claimed profile. A comparison or review page wants inclusion with evidence — real differentiators, pricing, proof — not a pitch. A community thread is entered honestly, with a real answer from a real account, or left alone. A publication wants the data or story its page is missing. Write the ask so the person who maintains that page can act on it in one sitting.
Run it like pipeline
Track each target as a row: source, page, answers it fed, whether it mentions the brand today, ask type, the human contact, status. Work the top of the list first; small placements land fastest and compound.
Verify the placement landed in answers
After a placement goes live, re-ask the questions that source was feeding and compare. If the answers do not move within a re-measure cycle, either the source mattered less than the count suggested, or the mention lacks the substance engines quote — specifics, numbers, and comparisons get cited; adjectives do not. Fix the mention before adding new targets.
What good looks like
The best operators notice the shape of what engines quote from each source — a comparison table, a price, a spec — and ask for that placement, not a logo on a partner wall. The mediocre version is generic link-building outreach re-sent with new words in the subject line, ordered by domain authority, never re-measured. Good output attaches evidence to every target — the answers that source fed — so each outreach message writes itself, and every closed row has a before-and-after answer pair proving it mattered.
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 · 42 lines · 90 tokens per session scan A 9f52717504d7
citation-gap-outreach is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 619 once invoked, about $0.0005 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
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…
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,"…
press-media-relations
Use when the user asks to "build a media list for my launch", "write a launch press release", or "pitch press under embargo"; produces a three-tier media and analyst list (Tier 1 exclusive candidates, Tier 2 vertical press, Tier 3 communities and newsletters), an embargo pitch timing skeleton keyed to the…
launch-monitor
Use when the user asks to "monitor my launch", "track our Product Hunt / Hacker News ranking", or "watch the launch window"; runs the T-0 to T+30 window watch — pre-launch instrumentation verification (UTM/event checks, the upstream of RAMP P1), HN rank/points/comments polling with a comments-over-points flamewar…