fly

fly is a skill for Claude Code from saadshahd/moo.md. It costs 40 tokens per session (669 once invoked), scanned A, original, MIT.

A coordination skill for sending one thought through several agents working on separate parts of a project. It uses the project's existing tools and records, and stops if the needed coordination setup is missing.

In plain words
What is it for?
Use it to divide a destination into independent parts, run those parts concurrently, and track what each agent did across worktrees or the project's existing log.
Why use it?
It prevents parallel work from losing details or having agents change the same part at once.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the hunch plugin — 1 skill shipped together

Good fit Use it to divide a destination into independent parts, run those parts concurrently, and track what each agent did across worktrees or the project's existing log.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saadshahd/moo.md/fly
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 saadshahd/moo.md --skill fly
Clone the repo
git clone --depth 1 https://github.com/saadshahd/moo.md

Made for: Claude Code.

Or install hunch, the plugin that ships this one along with the rest of its 1 skill.

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.

agentmods badge for fly

README.md
[![agentmods](https://agentmods.dev/badge/skills/saadshahd/moo.md/fly/github.svg)](https://agentmods.dev/skills/saadshahd/moo.md/fly)
Your own site
<a href="https://agentmods.dev/skills/saadshahd/moo.md/fly"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/fly/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.

agentmods 80×15 button for fly

Your own site · 80×15
<a href="https://agentmods.dev/skills/saadshahd/moo.md/fly"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/fly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 669 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00669
Opus 5 $0.00020 $0.00334
Sonnet 5 $0.00008 $0.00134
Haiku 4.5 $0.00004 $0.00067

Measured 2d ago against content hash ea7eca269f3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fly 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 2d 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.

hunch/skills/fly/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the pilot of one thought. Several agents fly its parts at once; you never fly a part. Speak in the thought's own words, and ask the user nothing before takeoff.

Words

  • destination — what will be true when it lands, what it must not touch, and every detail the thought named. In the user's words.
  • part — the piece of the destination one agent carries and may change alone. Two agents never share a part.
  • log — what the medium already keeps of what happened. Never a file made for the flight.

Medium

The flight uses what is already there. Find each of these in the project and the harness before anything else; add nothing for the flight's sake.

Needed Use what exists
Agents flying their parts at once Solo spawn_agent, the Agent tool, claude -p in a terminal, one worktree per part
The log: where every agent reads the destination and where what happened shows git across worktrees, the Solo scratchpad, the agents' own returns, the tracker or PR the project already uses
Where the user looks the running app, a browser they can drive

One of the three is missing → say which and stop.

Takeoff

  1. Read the thought back as the destination, in the log, where the user can see it. Do not wait for a yes: a correction from the user changes it for every agent.

  2. Cut the destination into parts. An agent not worth its own warm-up is not a part. One part → say so and stop.

  3. Brief each agent in plain words:

    You fly `<part>` of the destination in <log>. Read the destination before you start and before every change you commit.
    
    Stop, say why in <log>, and wait, when any holds:
    - your part needs another's part
    - your part needs the destination changed
    - you need a fact you cannot get
    
    When you believe your part is done: stop and state what you did against your part. You do not land the flight.
    
  4. Start every agent. A start that fails stays in the log as a part not flown.

  5. Bring up where the user looks. Say what they will see first, and roughly when.

Read the full file on GitHub · 58 lines

Files

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.

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.

  1. 2d ago First seen · 58 lines · 40 tokens per session scan A ea7eca269f3a

Subscribe to this mod's changes

fly is a skill published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 669 once invoked, about $0.0002 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 2026-09-07.