What is NorthwoodsFleet?

A model-routing service that sends a task to a selected Workers AI model based on a hint such as code, translation, reflection, or research. It returns the response together with the model used and the reason for routing.

Use it for code reasoning, multilingual translation, reflective responses, research-heavy questions, second opinions, and fact-checking when the configured service is available.

It provides one way to choose different models for different kinds of work. This can help keep model selection separate from the rest of an application or workflow.

NorthwoodsFleet — Skill for Claude Code by NorthwoodsSentinel

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 NorthwoodsSentinel/northwoods-pack --skill northwoods-fleet

Clone the repo

git clone --depth 1 https://github.com/NorthwoodsSentinel/northwoods-pack

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/northwoodssentinel/northwoods-pack/northwoods-fleet/github.svg)](https://agentmods.dev/skills/northwoodssentinel/northwoods-pack/northwoods-fleet)

Your own site

<a href="https://agentmods.dev/skills/northwoodssentinel/northwoods-pack/northwoods-fleet"><img src="https://agentmods.dev/badge/skills/northwoodssentinel/northwoods-pack/northwoods-fleet/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/northwoodssentinel/northwoods-pack/northwoods-fleet"><img src="https://agentmods.dev/badge/skills/northwoodssentinel/northwoods-pack/northwoods-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 574 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.00574
Opus 5.5	$0.00033	$0.00230
Sonnet 5.5	$0.00017	$0.00115
Haiku 4.5	$0.00008	$0.00057

Measured 1mo ago against content hash dbba12078902, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

NorthwoodsFleet scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://localhost:31337/notify \

pai-skills/northwoods-fleet/SKILL.md · 59 lines

What it actually says

Customization

~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/NorthwoodsFleet/

Voice Notification

curl -s -X POST http://localhost:31337/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Routing through the fleet"}' \
  > /dev/null 2>&1 &

NorthwoodsFleet — Model Router

Calls the deployed Northwoods Pack Worker to route a query through the right Workers AI model based on hint.

Workflow

Read pack.url and auth.token from ~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/NorthwoodsPack/CONFIG.md.
POST {pack.url}/fleet/route with X-Pack-Token: {auth.token} and a JSON body.

Request

curl -s -X POST "$PACK_URL/fleet/route" \
  -H "Content-Type: application/json" \
  -H "X-Pack-Token: $TOKEN" \
  -d '{
    "task": "the user query as a single prompt",
    "hint": "code",
    "max_tokens": 512
  }'

Returns {response, model_used, route_reason, hint_received}.

Hint values

Hint	Routes to	When to use
`code`	Llama 4 Scout (US)	Code questions, technical reasoning
`translate`	Mistral Small 3.1	Multilingual / translation
`reflect`	Gemma 3 12B	Measured, reflective register
`research`	Llama 4 Scout (stub — Perplexity in v0.3)	Research questions
`factcheck`	Llama 4 Scout (stub — multi-model in v0.3)	Verification questions
(none)	Llama 4 Scout (default)	Anything else

Failure behavior

If the Worker returns an error or is unreachable, surface the error to the user. Do NOT silently fall back to a different model — the route_reason is part of the contract.

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.

1mo ago First seen · 59 lines · 83 tokens per session scan A dbba12078902

Subscribe to this mod's changes

NorthwoodsFleet is a skill published in the GitHub repository NorthwoodsSentinel/northwoods-pack (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 574 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents adhd cloudflare-workers mcp personal-ai sovereignty

hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…

CoWork-OS/CoWork-OS · 155 tokens

cli-anything

Drive desktop apps (LibreOffice, GIMP, Blender, Inkscape, Audacity, Draw.io, Kdenlive, Shotcut, Krita, FreeCAD, MuseScore) headless through CLI-Anything harnesses with JSON output, instead of clicking through the app window with nativeapp.

CoWork-OS/CoWork-OS · 65 tokens

hyperframes-cli

HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the…

CoWork-OS/CoWork-OS · 77 tokens

worker-pool

Create, route, supervise, and communicate with Sutando workers.

sonichi/sutando · 17 tokens

process-hygiene

Report, and with --reap stop, orphaned processes that interrupted agent test runs left behind in per-session scratchpads (PPID 1, this user, older than 2 h by default, cwd inside /claude- / / /scratchpad, and that session has ended). --spotlight keeps Spotlight from indexing scratchpad churn. For Sutando developers…

sonichi/sutando · 103 tokens

macos-tools

Native macOS integrations via AppleScript. No API keys needed — works on any Mac.

sonichi/sutando · 52 tokens

NorthwoodsFleet