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 multichannel-campaign-buildergit 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/multichannel-campaign-builder)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/multichannel-campaign-builder"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multichannel-campaign-builder/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/multichannel-campaign-builder"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multichannel-campaign-builder.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 | $0.00139 | $0.01308 |
| Opus 5 | $0.00069 | $0.00654 |
| Sonnet 5 | $0.00028 | $0.00262 |
| Haiku 4.5 | $0.00014 | $0.00131 |
Grade A, and why
multichannel-campaign-builder 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Applies when a sequence needs writing, not a single message. Produces three angles, then every touch in the cadence, checked before delivery.
A sequence is not five emails about the same thing
The common failure isn't a bad first message — it's five follow-ups that all say the same thing in a slightly more desperate tone. The prospect ignored the argument once; repeating it four times with "just bumping this" on top adds nothing except a reason to block the sender.
Every touch needs its own reason to exist. That means a fresh angle each time, a different CTA shape than the one before it, and a subject line that isn't a variation on the last. Sequence coherence — angles progressing rather than repeating, consecutive cross-channel touches not doubling up — is what separates a campaign from a nag.
Get the brief before writing anything
Ask once, in a single message, for whatever is missing: what they sell and the problem it solves in one sentence; the target persona, company type and size; whether a signal or trigger exists; and the channel mix. Ask about tone and any banned words if they have them.
If something essential is missing — the persona, what they actually sell — ask one short question and stop. Don't fill the gap with a plausible guess; a sequence written for the wrong buyer is worse than no sequence, because it reads finished.
The campaign type follows from whether a signal exists and where it came from, and it drives the framing, the cadence and the sequence shape:
- Cold outbound — no signal. Relevance has to be argued from research.
references/campaign-type-cold-outbound.md. - Social selling — the prospect engaged with something.
references/campaign-type-social-selling.md. - Employee advocacy — reaching people who engaged with a colleague's post.
references/campaign-type-employee-advocacy.md.
Load only the one that applies.
Three angles, then commit
Produce exactly three distinct angles and recommend one. Distinct means they'd land differently on the same reader, not three phrasings of one idea. Where a signal exists, the first angle is built on it.
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/angle-framework.md 6.0 KB
- references/base-copywriting-rules.md 6.3 KB
- references/campaign-type-cold-outbound.md 2.4 KB
- references/campaign-type-employee-advocacy.md 2.4 KB
- references/campaign-type-social-selling.md 2.3 KB
- references/cta-framework.md 5.2 KB
- references/email-rules.md 3.0 KB
- references/linkedin-rules.md 2.9 KB
- references/quality-check.md 4.8 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.
- 9d ago First seen · 80 lines · 139 tokens per session scan A 63a2517f3597
multichannel-campaign-builder is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 1,308 once invoked, about $0.0007 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
cold-email-personalizer
A tool that writes personalised cold emails, which are unsolicited messages sent to potential customers or partners, using information about each person.
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.
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…
a-b-testing
Design statistically sound GTM experiments for copy, channels, landing pages, sequencing, pricing, and funnel conversion. Produces hypothesis, sample-size logic, success metrics, test plan, analysis method, and scale/stop/kill recommendation. Use when planning A/B tests, split tests, or experiment roadmaps.
attribution
Build practical B2B attribution models across first touch, lead creation, opportunity creation, multi-touch, account-based influence, and sales-sourced revenue. Produces model comparison, UTM governance, source-of-truth rules, and channel ROI view. Use when marketing and sales disagree on source or ROI.
campaign-analytics
Analyze campaign performance from deliverability through revenue: delivery, engagement, replies, meetings, SQOs, pipeline, CAC, and payback. Produces diagnostic scorecard, root-cause analysis, benchmark comparison, and next-action plan. Use when deciding whether to scale, fix, or kill campaigns.