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 0xDarkMatter/claude-mods --skill fleet-workergit clone --depth 1 https://github.com/0xDarkMatter/claude-modsWrote 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/0xdarkmatter/claude-mods/fleet-worker)<a href="https://agentmods.dev/skills/0xdarkmatter/claude-mods/fleet-worker"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/fleet-worker.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.04171 |
| Opus 5 | $0.00044 | $0.02086 |
| Sonnet 5 | $0.00017 | $0.00834 |
| Haiku 4.5 | $0.00009 | $0.00417 |
Grade A, and why
fleet-worker 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 7d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fleet-worker
Run a cheap headless Claude Code worker on a cheaper model and let an Opus orchestrator (this session) fan workers out in parallel, then verify and land their work. The worker keeps Claude Code's entire tool harness (Read/Write/Edit/Bash/Glob/Grep/Task/MCP/hooks) — only the brain is swapped to a cheaper model via env — a cheaper Anthropic model (Sonnet/Haiku) or a non-Anthropic endpoint. GLM-5.3 on z.ai is the default worked example; the mechanism is provider- and model-agnostic (any Anthropic-compatible endpoint).
Want to offload to Grok (xAI's
grokCLI)? That's not this skill. Every fleet-worker brain is aclaude -pprocess pointed at an Anthropic-compatible endpoint. Grok Build CLI is its own binary and protocol (grok -p, auth viaGROK_DEPLOYMENT_KEY), not aclaude -pwrapper — so it can't ride fleet-worker's launcher. Grok is a first-class worker in fleetflow instead (alongside Codex), which spawns heterogeneous OS-process workers of different binaries — now its own repo at 0xDarkMatter/fleetflow, mounted as the/fleetflowskill. Use fleetflow for a Grok lane or any mixed-provider fan-out.
This is the spawning layer. fleet-ops is the landing layer.
fleet-worker produces branches cheaply; fleet-ops lands them through a test gate
with your review. See references/fleet-ops-handoff.md.
The architecture crux: per-agent model = process isolation
ANTHROPIC_BASE_URL and the ANTHROPIC_DEFAULT_*_MODEL mapping vars are
process-global — read once per claude process, applied to every model
call it makes (including in-process Task subagents). There is no per-agent
override. So you cannot keep one Opus session and have its subagents secretly
run on GLM. The only way to pair a GLM-brained agent with an Opus orchestrator is
a separate OS process with its own env block. That process is fleet-worker.
What ships with it
10 files 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.
- assets/route.js 3.5 KB runs code
- assets/worker-settings.json 43 B
- references/fleet-ops-handoff.md 5.0 KB
- references/fleet-worker-spec.md 16 KB
- references/model-routing.md 6.4 KB
- scripts/fleet-collect.sh 2.9 KB runs code
- scripts/fleet-doctor.sh 10 KB runs code
- scripts/fleet-worker 6.2 KB
- scripts/fleet-worker.ps1 5.5 KB runs code
- tests/run.sh 11 KB runs code
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.
- 7d ago First seen · 298 lines · 87 tokens per session scan A 8f07e863afb6
fleet-worker is a skill published in the GitHub repository 0xDarkMatter/claude-mods (32 stars, last pushed 14d ago), licensed MIT. It adds 87 tokens to every session and 4,171 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 2026-08-30.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
analytics-interpretation
Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.
app-namer
Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.
in-app-events
Generates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep link configuration. Use when creating events for App Store visibility, engagement campaigns, or seasonal promotions.