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 5.5 | $0.00073 | $0.00686 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago Changed · +3 lines 0146e750a362
- 1mo 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 (221 stars, last pushed 7d ago), licensed MIT. It adds 182 tokens to every session and 1,716 once invoked, about $0.0007 per session on Opus 5.5. 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
cold-outreach
Use when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits, the compliant opt-out footer. NOT SPF/DKIM/DMARC setup (that is email-deliverability), NOT sourcing the list (that is lead-gen), NOT life…
linkedin-outreach
Use when running LinkedIn social selling as a repeatable motion — Sales Navigator saved searches and trigger alerts, weekly request budgets, fixing a low acceptance rate, turning profile views and post engagers into warm threads, logging every touch. NOT the note or DM copy (that is cold-outreach), NOT the deal after…
Cold Email Writer
Write personalized cold outreach emails to hiring managers and founders - specific, human, not a pitch deck.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
agent-browser
Drive a real headless Chromium on the workspace host to read pages, fill forms, click buttons, run JS, and take screenshots. Use this whenever you need more than a plain HTTP fetch — pages that require JS to render, pages with an interactive element you have to click through, or when you want an accessibility-tree…
find-leads
Find qualified B2B leads with OpenOutreach — run openoutreach find N [emails], read the CSV it prints on stdout, and hand the rows to whatever sends. Use when the user wants leads, prospects, an ICP-matched contact list, or asks what a campaign already has. Also covers first-run setup (openoutreach init), openoutreach…