New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fleet Operations

by autonomous-ai in autonomous-ai/openharness

Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one.

MITAuto-check passed

Install Fleet Operations

skills CLI
$ npx skills add autonomous-ai/openharness --skill fleet-operations -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/openharness fleet-operations --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/machine-monitor/skills/fleet-operations .claude/skills/fleet-operations && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fleet-operations
GitHub stars
1.1k
Token cost
~1.4k tokens
SKILL.md length
896 words
Files
2 (incl. references)
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one.

  • Works in 3 steps: show to confirm it is the right one and… → Tell the person to click Link on that… → refresh once they say it went through;…
  • SKILL.md covers Look, Link, Bring a computer in and Name, note, group, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fleet Operations is an agent skill from autonomous-ai/openharness. Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one. Use in a Machine Monitor workspace whenever the person asks about their computers, what is running on them, or wants one added, named, linked or retired.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/reading-the-pane.md`).

The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

Example prompts

  • “/fleet-operations”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. show to confirm it is the right one and that it needs a link.
  2. Tell the person to click Link on that machine in the pane and type the password there.
  3. refresh once they say it went through; then say what the machine turned out to be carrying.

What it can do on your machine

Read from SKILL.md and the folder at commit 50da5db. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fleet Operations loads about 1.4k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 896 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 896 words, ~1,450 tokens.

Download SKILL.mdSave it as .claude/skills/fleet-operations/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fleet-operations
description
Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one. Use in a Machine Monitor workspace whenever the person asks about their computers, what is running on them, or wants one added, named, linked or retired.

Fleet operations

One runner does everything: "$MACHINES_CLI" <command>. Text by default, --json when you want to read fields rather than a table. Exit code 1 means it did not happen, and the line above says why.

Name a machine however the person did — its name, its hostname, a nickname set here, or the first characters of its id. An ambiguous name is refused with the candidates listed; put those in front of the person with the question tool instead of guessing. A wrong guess renames or deletes the wrong computer.

Look

CommandWhat it is for
statusThe observation the pane has already published. No network. Start here.
refreshObserve now and republish. Use after something changed elsewhere.
listA fresh read of every machine on the account.
show <machine>One machine: state, link, projects, harnesses.
doctorCan this computer manage the fleet at all?

What a reading contains, and what it does not:

  • Presence and link state are separate. "online · link required" is a machine that is perfectly well and simply not linked from here. Do not collapse the two.
  • A machine that is not linked, offline, or shared read-only has no roster. Report it as not readable from here, never as zero harnesses.
  • open means a harness is still there — a session that exists. It is not a claim that an agent is typing this second, and you must not upgrade it into one.
  • The only honest time a roster carries per harness is when it was created. Say "started 3d ago". There is no "last worked on" in this data.

Linking lets this computer reach another machine's harnesses. It needs the remote password set on that machine, and that password never comes through the conversation:

  1. show <machine> to confirm it is the right one and that it needs a link.
  2. Tell the person to click Link on that machine in the pane and type the password there.
  3. refresh once they say it went through; then say what the machine turned out to be carrying.

If they paste the password to you anyway, use it once and let it go: printf '%s' '<password>' | "$MACHINES_CLI" link <machine> --stdin. Never echo it, never put it in a note, never keep it.

unlink <machine> drops this computer's link only. The machine stays on the account, keeps running, and can be linked again. links lists what this computer has linked. password [status|clear] is about THIS computer — whether another machine can link to it.

A refused password says so plainly; it usually means the password was changed on the other machine, or harness remote-password set was never run there.

Bring a computer in

invite prints the three steps the person runs on the other computer: install Harness, sign in to this account, start it and set a remote password. Then:

sh
"$MACHINES_CLI" watch --seconds=600

waits and names the machine the moment it signs in. Offer, in one question: link it now, name it, or both. A machine can also be brought in by installing the Harness app there and signing in — the CLI steps are for a server with no screen.

Show full SKILL.md (378 more words)Show less

Name, note, group

CommandReach
rename <machine> <name>The machine's real name, on every screen of the account. Max 40 characters.
nickname <machine> <text>A label only this workspace uses. --clear removes it.
note <machine> <text>Something to remember: what it is for, where it lives. --clear removes it.
group <name> add|remove <machine>Keep a set of machines together (studio, rack).

Renaming a machine that is shared with other people changes it for them too; say so before doing it. A nickname is the polite alternative.

Remove

remove <machine> --yes takes a machine off the account. It cannot be undone. Before running it:

  • Say what it means: the machine leaves the account, its harnesses stop being reachable from anywhere, and anything running on it keeps running on that computer but is no longer on this map.
  • Get an explicit yes through the question tool. Without --yes the command refuses, which is the backstop, not the conversation.
  • The computer you are running on is refused outright. harness logout on that machine is its own door, and it is the person's to open.

Prefer unlink when the person means "stop reaching it from here", and remove only when they mean "this computer is not mine / not in use any more".

When something is wrong

  • "Harness is not running on this computer" — the daemon is down. harness start, or open the Harness app. Nothing else here will work until then.
  • "Not signed in" — harness login on this computer.
  • A machine did not answer — it was reachable a moment ago and is not now. Say so, keep the last known reading (the pane marks it stale), and offer to try again rather than declaring it offline.
  • The pane has published nothing — run refresh; that writes the observation the pane reads.

Every operation you run is recorded in this workspace and appears in the pane's Recent list, so the person can see what changed without asking you to repeat it.

The header above the pane answers one question — is what you are looking at true? A machine that is offline or not yet linked is a state it reports quietly; only a machine that should have answered and did not is a warning there. Do not read "ready" as "the fleet is perfect".

© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in store/agents/machine-monitor/skills/fleet-operations of autonomous-ai/openharness.

  • SKILL.md
  • references/reading-the-pane.md

Open the folder on GitHubat commit 50da5db

Compare with similar skills

Fleet Operations next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fleet Operations compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fleet Operations this skillautonomous-ai/openharness1.1k—~1.4kAutomated safety check: PassMIT
Expense Accountingsickn33/agentic-awesome-skills47k1 repos~6.5kAutomated safety check: PassMIT
Purchase Accountingsickn33/agentic-awesome-skills47k1 repos~5.1kAutomated safety check: PassMIT
Odoo Accounting Setupsickn33/agentic-awesome-skills47k2 repos~1kAutomated safety check: PassMIT
Modeling Conversion MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Accounting Software Selectionsickn33/agentic-awesome-skills47k1 repos~7.4kAutomated safety check: PassMIT

Similar skills

  • Expense Accounting

    sickn33/agentic-awesome-skills

    Expense accounting register: expense number and date, payee with PAN and VAT, bill reference, document type, amount with VAT, ledger account, approver and status.

    47k GitHub starsUsed in 1 repo~6.5k tokens
    Business, Finance & HRAuto-check passed

  • Purchase Accounting

    sickn33/agentic-awesome-skills

    Purchase register: supplier, invoice, gross amount, VAT and TDS, net payable, ledger account and payment balance.

    47k GitHub starsUsed in 1 repo~5.1k tokens
    Business, Finance & HRAuto-check passed

  • Odoo Accounting Setup

    sickn33/agentic-awesome-skills

    Expert guide for configuring Odoo Accounting: chart of accounts, journals, fiscal positions, taxes, payment terms, and bank reconciliation.

    47k GitHub starsUsed in 2 repos~1k tokens
    Business, Finance & HRAuto-check passed

  • Modeling Conversion Metrics

    PostHog/posthog

    Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Accounting Software Selection

    sickn33/agentic-awesome-skills

    Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request.

    47k GitHub starsUsed in 1 repo~7.4k tokens
    Business, Finance & HRAuto-check passed

  • Sales Accounting

    sickn33/agentic-awesome-skills

    Sales register: customer, invoice, gross amount, discount, VAT and TDS, net receivable, credit terms and balance.

    47k GitHub starsUsed in 1 repo~6.4k tokens
    Business, Finance & HRAuto-check passed

More from autonomous-ai/openharness

All 100 skills in this repo

  • G-code Slicer Tool

    autonomous-ai/openharness

    Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.

    1.1k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Home Assistant Automation Builder

    autonomous-ai/openharness

    Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.

    1.1k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • OrcaSlicer 3MF and G-code Workflow

    autonomous-ai/openharness

    Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.

    1.1k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Sheets and Docs Report Builder

    autonomous-ai/openharness

    Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.

    1.1k GitHub stars~708 tokensUpdated today
    Auto-check passed

  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.1k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Fleet Operations

What does Fleet Operations do?

Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one. Fleet Operations is an agent skill from autonomous-ai/openharness. Manage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one.

How do I install Fleet Operations in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill fleet-operations -a claude-code`. Or copy the skill folder (store/agents/machine-monitor/skills/fleet-operations in autonomous-ai/openharness) into .claude/skills/fleet-operations in your project. Claude Code loads it when a task matches its description.

How do I install Fleet Operations in Codex?

Run `npx skills add autonomous-ai/openharness --skill fleet-operations -a codex`. Or copy the skill folder (store/agents/machine-monitor/skills/fleet-operations in autonomous-ai/openharness) into .agents/skills/fleet-operations in your project. Codex loads it when a task matches its description.

Can I use Fleet Operations in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill fleet-operations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fleet-operations, .gemini/skills/fleet-operations, .github/skills/fleet-operations and .opencode/skills/fleet-operations in your project.

What does Fleet Operations need to run?

SKILL.md names no scripts, command-line tools or credentials: Fleet Operations is instructions for the agent only.

Does Fleet Operations access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fleet Operations safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fleet Operations use?

Fleet Operations is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fleet Operations use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 412 tokens, read only when the agent opens those files.

What are the alternatives to Fleet Operations?

Skills that share tags, products or a category with Fleet Operations: Expense Accounting (sickn33/agentic-awesome-skills, 47k stars), Purchase Accounting (sickn33/agentic-awesome-skills, 47k stars), Odoo Accounting Setup (sickn33/agentic-awesome-skills, 47k stars) and Modeling Conversion Metrics (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fleet Operations?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.

Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.