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 mishahanin/heading-os --skill cold-sweepgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/cold-sweep)<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.
<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>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 | $0.00120 | $0.01738 |
| Opus 5 | $0.00060 | $0.00869 |
| Sonnet 5 | $0.00024 | $0.00348 |
| Haiku 4.5 | $0.00012 | $0.00174 |
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.
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_corereadscrm-health.py --json, routes each overdue contact, and depositsemail_sendcards withdraft_status: needs_draft. This runs either on the daemon's schedule (06:30 local time, when enabled) or viascripts/cold-sweep.pyfor a manual run (daemon-free, in-processappend_cards). - Voice + judgment (this skill): fills the
needs_draftcards with a ~150-word nudge in Misha's voice and flips them toready_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
- Read
reference/misha-voice.md(voice, maritime inventory, "what Misha never says"). - Apply
.claude/rules/voice.md,.claude/rules/humanization.md,.claude/rules/hidden-chars.md,.claude/rules/voss.md. - Read the queue store
outputs/operations/action-queue/queue.json(read-only) to discover cards. The targets are cards withaction_type: "email_send"ANDstatus: "pending"ANDdraft_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-processappend_cards; works with the bridge daemon down). --dry-run(if the CEO passed it): runpython3 scripts/cold-sweep.py --dry-runand present the routed cards without drafting. Stop after presenting.
Re-read queue.json after a manual sweep to pick up the new cards.
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.
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.
- 5d ago Changed 0cc61e8d3fe9
- 9d ago First seen · 111 lines · 120 tokens per session scan A d0ab61bfe1ee
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.
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.
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.
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.
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.
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.
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.