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 outreach-executiongit 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/outreach-execution)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/outreach-execution"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/outreach-execution/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/outreach-execution"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/outreach-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 114 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 214 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 97 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00130 | $0.03509 |
| Opus 5 | $0.00065 | $0.01754 |
| Sonnet 5 | $0.00026 | $0.00702 |
| Haiku 4.5 | $0.00013 | $0.00351 |
Grade A, and why
outreach-execution 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- outreach-execution — 98% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template placeholders
Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.
{{CRM}}— Your CRM (e.g. HubSpot, Attio, Salesforce){{SENDER_ROSTER}}— The people who can send outreach, with which channels each has connected (email, LinkedIn){{AWARENESS_SENDER}}— Senior exec (usually a founder or CxO) who runs the no-pitch awareness touch to decision makers{{HIGH_TIER_SENDER}}— Primary sequence sender for your top account tiers (usually your most senior GTM seller){{LOW_TIER_SENDER}}— Primary sequence sender for your lower account tiers{{TIER_MODEL}}— Your account tiering scheme and which tiers count as "high" vs "low" (e.g. Gold/Diamond = high, Silver/Bronze = low){{APPROVAL_OWNER}}— The human who reviews and approves staged sequences before anything sends{{MULTITHREAD_THRESHOLD}}— Company size above which an executive multi-thread must run in parallel with the primary sequence (default: >200 employees){{LARGE_COMPANY_THRESHOLD}}— Company size above which executives are never auto-contacted without approval (default: 100+ employees){{VOICE_SOURCE}}— Where sender voice lives: saved voice guides, past approved messages, or both{{RESOURCE_LIBRARY}}— Single source of truth for shareable URLs: booking links, demo video, trust/security docs, one-pagers{{AUTO_APPROVE_CARVEOUT}}— The one narrow scenario (if any) where a sequence may send without human approval (default: none — everything is approved)
What this skill produces
A staged outreach sequence — queued for approval, never sent — for the right contact(s), with sender, sequence steps, and a written outreach rationale attached. {{APPROVAL_OWNER}} reviews, edits if needed, and approves before anything goes out.
When the user asks about outreach strategically ("how should our cold emails sound," "what is the right cadence shape"), the output is a point of view anchored in {{VOICE_SOURCE}} and past approved messages — not a sequence.
What ships with it
3 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 · 229 lines · 130 tokens per session scan A f8380005ee9d
outreach-execution is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 130 tokens to every session and 3,509 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 2026-09-03.
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…