cold-sweep

cold-sweep is a skill for Claude Code from mishahanin/heading-os. It costs 120 tokens per session (1,738 once invoked), scanned A, original, Apache-2.0.

A workflow for turning overdue customer contacts in a CRM into prioritised email drafts. A CRM is a system for tracking customer relationships and follow-ups.

In plain words
What is it for?
Use it to route overdue contacts, write follow-up nudges in a specified voice, and place them in an approval queue.
Why use it?
It clears the backlog while leaving the actual sending decision to a person.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to route overdue contacts, write follow-up nudges in a specified voice, and place them in an approval queue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mishahanin/heading-os/cold-sweep
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 mishahanin/heading-os --skill cold-sweep
Clone the repo
git clone --depth 1 https://github.com/mishahanin/heading-os

Made for: Claude Code.

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 cold-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/cold-sweep/github.svg)](https://agentmods.dev/skills/mishahanin/heading-os/cold-sweep)
Your own site
<a href="https://agentmods.dev/skills/mishahanin/heading-os/cold-sweep"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/cold-sweep/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 cold-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/mishahanin/heading-os/cold-sweep"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/cold-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,738 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.
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 $0.00120 $0.01738
Opus 5 $0.00060 $0.00869
Sonnet 5 $0.00024 $0.00348
Haiku 4.5 $0.00012 $0.00174

Measured 5d ago against content hash 0cc61e8d3fe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cold-sweep 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 5d 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.

.claude/skills/cold-sweep/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cold-sweep

Turn the overdue-contact backlog into prioritised, cited, voice-drafted nudges sitting in the Action Queue for one-click go/no-go. scripts/cold_sweep_core.py does the deterministic routing: who, and at what priority. This skill does only the part that needs judgment and voice - the actual draft body.

Split of responsibilities (plan 2026-06-03, Design Decision 5):

  • Deterministic + headless: cold_sweep_core reads crm-health.py --json, routes each overdue contact, and deposits email_send cards with draft_status: needs_draft. This runs either on the daemon's schedule (06:30 local time, when enabled) or via scripts/cold-sweep.py for a manual run (daemon-free, in-process append_cards).
  • Voice + judgment (this skill): fills the needs_draft cards with a ~150-word nudge in Misha's voice and flips them to ready_for_review.

The CEO then approves+sends from the terminal with /queue approve <id> (or scripts/action-queue.py approve <id>) - a SYNCHRONOUS, watched send, daemon-free. This skill never sends; it only drafts into the queue.

Phase 0 - Load context

  1. Read reference/misha-voice.md (voice, maritime inventory, "what Misha never says").
  2. Apply .claude/rules/voice.md, .claude/rules/humanization.md, .claude/rules/hidden-chars.md, .claude/rules/voss.md.
  3. Read the queue store outputs/operations/action-queue/queue.json (read-only) to discover cards. The targets are cards with action_type: "email_send" AND status: "pending" AND draft_status: "needs_draft".

Phase 1 - Ensure cards exist

If there are no needs_draft cards in the queue:

  • Run a manual sweep: python3 scripts/cold-sweep.py (deposits DAEMON-FREE via the in-process append_cards; works with the bridge daemon down).
  • --dry-run (if the CEO passed it): run python3 scripts/cold-sweep.py --dry-run and present the routed cards without drafting. Stop after presenting.

Re-read queue.json after a manual sweep to pick up the new cards.

Read the full file on GitHub · 111 lines

Files

What ships with it

1 file 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.

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. 5d ago Changed 0cc61e8d3fe9
  2. 9d ago First seen · 111 lines · 120 tokens per session scan A d0ab61bfe1ee

Subscribe to this mod's changes

cold-sweep is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 1,738 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 2026-08-30.

Related

Other skills, from other repositories

shogun-bloom-config

An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.

yohey-w/multi-agent-shogun · 86 tokens

shogun-model-list

A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.

yohey-w/multi-agent-shogun · 73 tokens

shogun-model-switch

A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.

yohey-w/multi-agent-shogun · 83 tokens

shogun-screenshot

A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.

yohey-w/multi-agent-shogun · 149 tokens

shogun-readme-sync

A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.

yohey-w/multi-agent-shogun · 66 tokens

shogun-agent-status

A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.

yohey-w/multi-agent-shogun · 98 tokens