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 reach-outgit 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/reach-out)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/reach-out"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/reach-out/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/reach-out"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/reach-out.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 | $0.00182 | $0.01716 |
| Opus 5 | $0.00091 | $0.00858 |
| Sonnet 5 | $0.00036 | $0.00343 |
| Haiku 4.5 | $0.00018 | $0.00172 |
Grade A, and why
reach-out 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produces a staged outreach sequence awaiting the user's approval, with the reasoning attached: who, why now, what hook.
The motion table — this org's, not the skill's
This table is the org's motion library. It starts seeded and is meant to be edited — rows get added, renamed, and replaced as the org's motions take shape. Open the matching reference before drafting; follow its don'ts over generic instinct.
| Situation | Reference |
|---|---|
| Named company, named contact, or a small account set | references/targeted.md |
| An identified website visitor | references/website-visitor.md |
| A recurring or scheduled list run, cold volume | references/cold-list.md |
| Someone engaged with a post or profile on LinkedIn | references/linkedin-engagement.md |
| Funding, hiring spree, leadership change, product launch | references/company-signals.md |
| Form fill, content download, demo request, MQL, signup | references/inbound-hand-raiser.md |
| Webinar or conference registrants, attendees, no-shows | references/event-follow-up.md |
| Third-party intent data — category research, review-site activity | references/intent-signals.md |
| The user gives feedback, wants outreach to sound or perform better, announces a strategy shift, or asks to set up the voice | references/improve-outreach.md |
No row matches (win-back, referral, reply handling) → run the procedure below and say so in the reasoning. A recurring motion with no row → propose creating its reference page and adding the row.
references/improve-outreach.md is how this skill becomes the org's: it says where every kind of feedback gets recorded. Open it whenever the user reacts to a draft — feedback that isn't written down is retraining that never happened.
This org's voice and rules
Nothing recorded yet. Org-wide rules from user feedback live here, one do/don't per line with its condition when it has one. These outrank everything below except the user's live instruction.
Anchor on the hook
What ships with it
9 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.
- references/cold-list.md 3.0 KB
- references/company-signals.md 3.3 KB
- references/event-follow-up.md 3.3 KB
- references/improve-outreach.md 5.4 KB
- references/inbound-hand-raiser.md 3.7 KB
- references/intent-signals.md 2.9 KB
- references/linkedin-engagement.md 2.6 KB
- references/targeted.md 2.7 KB
- references/website-visitor.md 2.6 KB
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.
- 2d ago Changed · +3 lines 0146e750a362
- 9d ago First seen · 77 lines · 182 tokens per session scan A ab3b6470dc0b
reach-out is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 1,716 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
leadership-change-outreach
End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person) for…
news-signal-outreach
End-to-end news-triggered signal composite. Takes any piece of news — an article, LinkedIn post, tweet, announcement, event, trend, regulation, product launch, acquisition, layoff, expansion, or any other public event — and evaluates whether the companies or people mentioned are ICP fits. If yes, identifies the…
champion-move-outreach
End-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users), detects when they move to a new company, researches the new company for ICP fit, and drafts personalized outreach leveraging the existing relationship. Tool-agnostic — works with any people…
linkedin-outreach
End-to-end LinkedIn outreach campaign builder. Takes leads from Supabase, upstream skills, or CSV. Aligns on campaign goal and tone, writes personalized LinkedIn message sequences (connection request + follow-ups + optional InMail), presents for review, and exports for the user's outreach tool (Dripify, Botdog…
funding-signal-outreach
End-to-end funding signal composite. Takes any set of companies, detects recent funding events, qualifies against your company context, finds relevant people (buyers, champions, users), and drafts personalized outreach. Tool-agnostic — works with any company source, contact finder, and outreach platform.
hiring-signal-outreach
End-to-end hiring signal composite. Takes any set of companies, detects job postings that your product augments or replaces, finds relevant people (the hiring manager, buyers, champions, users), and drafts personalized outreach using the job role as the hook. Tool-agnostic — works with any company source, job board…