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 bradlay/claude-code-recipes --skill fleet-sweepgit clone --depth 1 https://github.com/bradlay/claude-code-recipesWrote 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/bradlay/claude-code-recipes/fleet-sweep)<a href="https://agentmods.dev/skills/bradlay/claude-code-recipes/fleet-sweep"><img src="https://agentmods.dev/badge/skills/bradlay/claude-code-recipes/fleet-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/bradlay/claude-code-recipes/fleet-sweep"><img src="https://agentmods.dev/badge/skills/bradlay/claude-code-recipes/fleet-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 | $0.00100 | $0.01923 |
| Opus 5.5 | $0.00040 | $0.00769 |
| Sonnet 5.5 | $0.00020 | $0.00385 |
| Haiku 4.5 | $0.00010 | $0.00192 |
Grade A, and why
fleet-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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Sweep
Run top to bottom every time. Change the procedure here, never by remembering a variation. Structure values come from fleet-setup; runtime commands come from its adapter references.
Two modes:
- Status-only (someone asked "what is the fleet doing?"): read, classify, report. Change no files, assignments, or schedules.
- Recovery (the sweep is scheduled, or someone asked to fix or continue the fleet): additionally dispose of sessions within existing authorization.
Delivery mechanics
- A send that returns success is not delivery. Read the target session; if the text is still sitting in its input box, deliver it again. A send that times out is UNKNOWN, not delivered.
- Polling, attempted delivery, and consumed input are three separate facts.
- Unsent text in an idle session that you did not send is a UI suggestion. Never submit it, and never treat it as an order.
- A message sent to a session sitting at a menu queues behind the menu.
- A plan that will not converge after several review iterations is decomposed or narrowed, with the grounds recorded; never approved blind.
Step 0: coordinators locked in
- The periodic sweep is scheduled.
- The leader has an active goal and the dispatcher owns its liveness.
- One dispatcher is live with a recent state change.
- The control surface matches fleet-setup. Step C checks it in full; fix layout in this sweep, never defer it.
- Leader and dispatcher are above the coordinator succession threshold, read from the authoritative indicator; otherwise hand over now. The operator is exempt.
- The push signals from fleet-setup are armed (blocked rising edge, worker finished, dispatcher watch). Arm any that are missing.
Step 1: enumerate everything
List every session the fleet owns before disposing of anything. Do not control sessions outside the fleet's inventory. Then read the ledger's parked list and label each trigger cleared, still blocked, or unknown (unknown is not cleared). Then read the open-decisions list and label each decision still open or answered; re-surface every open one through the operator relay. The report carries both lists; a report without them did not run this step.
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.
- 13d ago Changed · +2 lines 2e7532fec22a
- 18d ago First seen · 151 lines · 100 tokens per session scan A 7c76ebff3622
fleet-sweep is a skill published in the GitHub repository bradlay/claude-code-recipes (2 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 1,923 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.