multi-sender-rotation

multi-sender-rotation is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 75 tokens per session (658 once invoked), scanned A, original, MIT.

A plan for sharing LinkedIn outreach across several sender accounts when one account cannot handle the required volume. It defines how to size the sender group, divide prospects, set individual limits, and respond to warnings.

In plain words
What is it for?
Use it to plan sender pools, assign lead lists, set per-account outreach caps, stagger sending times, and maintain a spare account.
Why use it?
It reduces the risk of overloading one LinkedIn account and helps prevent multiple senders from contacting the same person or company. It also provides a replacement approach when an account becomes unavailable or restricted.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan sender pools, assign lead lists, set per-account outreach caps, stagger sending times, and maintain a spare account.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/multi-sender-rotation
Install

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.

Any agent
npx skills add swan-gtm/gtm-skills --skill multi-sender-rotation
Clone the repo
git clone --depth 1 https://github.com/swan-gtm/gtm-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for multi-sender-rotation

README.md
[![agentmods](https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-sender-rotation/github.svg)](https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-sender-rotation)
Your own site
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-sender-rotation"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-sender-rotation/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.

agentmods 80×15 button for multi-sender-rotation

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/multi-sender-rotation"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/multi-sender-rotation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00658
Opus 5 $0.00037 $0.00329
Sonnet 5 $0.00015 $0.00132
Haiku 4.5 $0.00007 $0.00066

Measured 9d ago against content hash 19571374ffcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

multi-sender-rotation 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.

skills/imad-badreddine/multi-sender-rotation/SKILL.md · 39 lines

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 when campaign volume exceeds what one account can safely send. It produces a sender-pool plan: how many accounts, how leads are split, per-account caps, and what happens when an account degrades.

The play

  1. Size the pool from the target, not the other way around: divide required daily connection requests by 20, the safe steady-state ceiling per warmed account. A 100-invite-per-day campaign is a 5-account pool.
  2. Only rotate warmed accounts. A new profile joins the pool after a full warm-up ramp, never on day one. Keep one warmed spare per five active senders: the bench rule. When an account degrades, the bench replaces it the same day.
  3. Split the lead list by account, never round-robin per message. Each prospect belongs to exactly one sender for the entire relationship: the one-voice rule. Dedupe by person and by company before launch so two senders never hit the same account.
  4. Stagger sending windows so the pool does not fire in one burst: each account keeps its own working hours, matched to its own timezone and history.
  5. Keep per-account caps individual. An account fresh off warm-up sends less than a veteran; never apply the pool average to every profile.
  6. On any warning: pull that account from rotation immediately, pause it 48-72 hours, and let the bench absorb its remaining volume. Never redistribute a paused account's leads mid-conversation; conversations wait for their owner.
  7. Review the pool weekly: acceptance rate and reply rate per account. One account trending down while others hold is an account problem; all accounts trending down together is a targeting or copy problem.

What good looks like

  • Experienced operators read per-account acceptance rates as an early-warning system; the mediocre version only watches campaign totals and misses the one account quietly dying inside a healthy average.
  • The common mistake is treating the pool as one big account: shared caps, shared list, leads bouncing between senders. Prospects notice a second stranger continuing a first stranger's conversation, and so does the platform.
  • Done well, losing any single account costs at most one-fifth of daily volume for two days, no prospect ever hears from two different senders, and the campaign total stays flat while individual accounts rest and rotate.

Read the full file on GitHub · 39 lines

Changes

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.

  1. 9d ago First seen · 39 lines · 75 tokens per session scan A 19571374ffcd

Subscribe to this mod's changes

multi-sender-rotation 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 658 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.