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 linkedin-7-day-warmupgit 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/linkedin-7-day-warmup)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/linkedin-7-day-warmup"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-7-day-warmup/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/linkedin-7-day-warmup"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-7-day-warmup.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 | $0.00075 | $0.00613 |
| Opus 5 | $0.00037 | $0.00307 |
| Sonnet 5 | $0.00015 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
linkedin-7-day-warmup 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run this before any new or dormant LinkedIn account sends its first campaign. It produces a seven-day activity schedule and a go/no-go decision for opening full outreach.
The play
- Confirm the account's starting state: brand new, dormant, or returning from a warning. A returning account restarts this plan from day 1, never mid-way.
- Days 1-2: 3-5 likes and 1 comment per day, up to 5 connection requests per day. Nothing else. The account is being watched hardest here.
- Days 3-4: 3-5 likes and 1-2 comments per day, up to 10 connection requests per day.
- Days 5-7: start light conversations with accepted connections, up to 15-20 connection requests per day.
- After day 7, settle into the steady state: 20 connection requests per day reached gradually, 5-10 likes and 2-3 comments daily, small profile updates weekly. Open full outreach.
- Send links only after a prospect has replied, never in a first message.
- If the account receives any warning or verification prompt at any point: pause all activity for 48-72 hours, then resume one level below where the warning happened.
What good looks like
- The operators who keep accounts alive treat a warning as a hard stop, not noise. The mediocre version shrugs it off, keeps sending, and turns a warning into a restriction.
- Consistency beats speed. Seven steady days outperform three aggressive ones: identical daily behavior is what makes the account look human, and rushed ramps are the number-one cause of verification prompts.
- Engagement is not filler. The likes and comments in the early days are what makes the connection requests that follow look like a person, not a script. Skipping them to "save time" defeats the plan.
- Done well, the account reaches 20 connection requests per day with zero verification prompts, and the first replies are already arriving from the day 5-7 conversations.
Rules
- MUST pause 48-72 hours after any warning or verification prompt, then resume one level down.
- MUST keep daily activity consistent; never compress two days of the ramp into one.
- NEVER send identical messages across prospects; vary every message.
- NEVER include a link before the prospect has replied.
- NEVER skip the engagement activity (likes, comments) and run connection requests alone.
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 · 39 lines · 75 tokens per session scan A c05cb8c0c031
linkedin-7-day-warmup is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 613 once invoked, about $0.0004 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
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…
distributor-outreach-email
Writes a sales outreach email to a film or content distributor introducing a completed project for acquisition consideration, including key commercial information an acquisitions team needs to evaluate the opportunity.
ai-cold-email
Generate personalized cold outreach emails using AI.
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.
outreach-strategist
Reviews and coaches your outreach with specific scoring, feedback, and rewrites.