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 ArcBlock/agent-skills --skill fleet-setupgit clone --depth 1 https://github.com/ArcBlock/agent-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/arcblock/agent-skills/fleet-setup)<a href="https://agentmods.dev/skills/arcblock/agent-skills/fleet-setup"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/fleet-setup/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/arcblock/agent-skills/fleet-setup"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/fleet-setup.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 | $0.00051 | $0.04001 |
| Opus 5.5 | $0.00020 | $0.01600 |
| Sonnet 5.5 | $0.00010 | $0.00800 |
| Haiku 4.5 | $0.00005 | $0.00400 |
Grade A, and why
fleet-setup 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Setup — one command, a few questions, the fleet is live
Any teammate runs /agentloop:fleet-setup, answers ≤4 defaulted questions, and gets a running
fleet — local (crontab) and/or cloud (claude routines) — from one catalog covering
multiple repos. Re-running reconciles (idempotent upgrade path). Config is generated, never
hand-written.
★ Interactive skill (AskUserQuestion is core) — never run unattended. Denied by the
deny-interactive-unattendedhook = you are in an unattended environment → stop and say "/agentloop:fleet-setup needs a human present"; do NOT silently apply defaults (setting up a schedule is a durable, outward action that must be human-confirmed).
How it splits (why local is code, cloud is you)
- LOCAL — a deterministic installer (
fleet/setup.ts) does everything: generate/reconciledeployment.json+repos.json, then reconcile the# agentloop-fleet:crontab block (one row per skill; each row runsdriver.ts --skill Xwhich handles checkout/install/cadence/ parallel across every covered repo). You just collect answers and run it. - CLOUD — routine creation goes through the RemoteTrigger tool (an MCP tool is yours to call, not a script's), so YOU render the prompt + create/update one routine per (repo×skill) from the same catalog. Same catalog + prompts as local; only the scheduling substrate differs.
fleet/setup.ts is also runnable directly for scripted/reproducible bootstrap
(bun fleet/setup.ts --runner me --repos "…" --local --apply); this skill is the guided wrapper.
Step 0 — collect facts (before asking; all cheap, read-only)
# plugin root the cron will read (stable marketplace clone; setup.ts auto-detects the same)
PLUGIN=~/.claude/plugins/marketplaces/arcblock-agent-skills/plugins/agentloop
[ -f "$PLUGIN/.claude-plugin/plugin.json" ] || PLUGIN=<the --plugin-dir this session loaded>
# runner default: lowercased first word of git user.name ("Robert Mao" → robert); else whoami
git config user.name; whoami
uname -s # Darwin → shlock, Linux → flock
crontab -l 2>/dev/null | sed -n '/# agentloop-fleet:begin/,/# agentloop-fleet:end/p' # existing block
cat ~/.agentloop-fleet/repos.json 2>/dev/null # existing catalog (reconcile, don't clobber)
ls -1 ~/Develop/arcblock 2>/dev/null # local clones you could cover via worktree mode
ls ~/.agentloop-fleet/env 2>/dev/null && echo "envFile present" # credentials; installer scaffolds it if absent
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 Changed 74687e043024
- 20d ago Changed · +3 lines · -86 tokens per session 2a4572ef9f34
- 1mo ago Changed c09c5639c350
- 1mo ago First seen · 236 lines · 137 tokens per session scan A e180d825f365
fleet-setup is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 4,001 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.