Ops Fleet logo

Ops Fleet

Organization
Lifecycle-Innovations-Limited
ops-fleet

OPS on-demand: This skill should be used when the user asks to "fleet dashboard", "CLIProxy sessions"…

Overview

PublisherLifecycle-Innovations-Limited
Repositoryclaude-ops
Skill nameops-fleet
Stars
543
Forks
64
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Lifecycle-Innovations-Limited on GitHub. Read the source before you install it.

Installation

Install the Ops Fleet AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-fleet
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Lifecycle-Innovations-Limited/claude-ops.git /tmp/claude-ops
mkdir -p .claude/skills
cp -r /tmp/claude-ops/claude-ops/skills/ops-fleet .claude/skills/ops-fleet
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ops Fleet in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ops Fleet on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ops Fleet is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OPS ► FLEET

Load ops-rules before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If AskUserQuestion / Workflow are missing, follow Rule 10 in ops-rules (Hermes: numbered options / two-turn Telegram card; delegate_task).

Unified, read-only operational dashboard for:

  • local Claude Code sessions and daemon state;
  • the configured CLIProxyAPI gateway;
  • the effective model catalog grouped by provider;
  • the canonical server-side auth-record pool and configured load-balancing policy;
  • recent inference-only request, error, and latency signals;
  • optional legacy local account-rotator utilization.

It renders state and never changes it. It does not consume the CLIProxyAPI usage queue, modify configuration, refresh credentials, switch accounts, or restart services.

Runtime sources

LayerSourceTruth represented
Claude sessionsclaude agents --jsonlive interactive/background session census
Claude daemonclaude daemon statuslocal supervisor/socket state
GatewayGET /CLIProxyAPI server identity, reachability, latency
Modelsauthenticated GET /v1/modelseffective client-visible model catalog
Poolsanitized helper/command JSONenabled/disabled/backup auth records, configured routing/retries, recent inference RED signals
Legacy rotatorlocal state file, opt-incompatibility utilization only; not canonical gateway pool truth

A protected model endpoint returning 401/403 means gateway reachable, auth required — not gateway down. A missing pool collector degrades only the pool panel; session and gateway rows still render.

Discovery and configuration

Claude binary

  1. CLAUDE_BIN
  2. command -v claude

CLIProxyAPI base URL

  1. CLIPROXYAPI_BASE_URL
  2. fleet.cliproxy_base_url in $PREFS_PATH
  3. Claude settings ANTHROPIC_BASE_URL
  4. portable fallback http://127.0.0.1:8317

Client authentication uses CLIPROXY_API_KEY or CLIPROXYAPI_API_KEY. Values are used only as request headers and are never printed.

Server-side pool snapshot

Preferred options, in order:

  1. CLIPROXYAPI_POOL_COMMAND — executable path that prints the sanitized JSON schema below. Shell command strings are rejected.
  2. CLIPROXYAPI_SSH_HOST plus optional CLIPROXYAPI_SSH_USER, or the equivalent fleet.cliproxy_ssh_host / fleet.cliproxy_ssh_user preferences. This invokes bin/ops-fleet-pool-snapshot, which may sudo only the fixed remote executable ${CLIPROXYAPI_REMOTE_HELPER:-/usr/local/libexec/cliproxy-fleet-snapshot}.

The public plugin intentionally has no real host, IP, username, or account identity defaults.

Invocation

Run and relay its output verbatim, stripping ANSI for a chat code block:

bash
${CLAUDE_PLUGIN_ROOT}/bin/ops-fleet $ARGUMENTS

Flags:

FlagBehavior
--once / --snapshotsingle render
--tui / --watch [secs]live alternate-screen TUI; q quits
--allinclude completed sessions when supported by Claude Code
--modelsexpand all effective model IDs
--no-pool / --no-remote / --no-ec2skip server-side pool collection
--legacy-accountsshow local rotator compatibility rows
--no-colorplain output

In a real terminal the command defaults to the TUI. Captured stdout defaults to one shot.

Output contract

Always render the dashboard first in a fenced code block. Then add one concise summary covering:

  • total sessions and any blocked/waiting sessions;
  • gateway reachability/auth/model count;
  • pool enabled/disabled/backup auth-record counts and configured routing strategy;
  • recent inference error rate, 429/5xx, and p95 latency;
  • any degraded data source.

End with one line noting that the live TUI is ${CLAUDE_PLUGIN_ROOT}/bin/ops-fleet --tui in a real terminal.

Read-only and safety guarantees

  • Never query /v0/management/usage-queue; it pops telemetry records.
  • Never require the remote Management API; lockouts or localhost-only management must not break fleet status.
  • Never print client or management keys.
  • Never return raw proxy logs or account identities.
  • Never treat local rotator state as the canonical remote pool.
  • Never report a missing optional collector as gateway failure.

Frequently asked questions

What does the Ops Fleet AI skill do?

OPS on-demand: This skill should be used when the user asks to "fleet dashboard", "CLIProxy sessions"…

Why use Ops Fleet on TypingMind?

Because you install it once and use it with any model. Ops Fleet is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ops Fleet in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-fleet. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ops Fleet?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ops Fleet?

As many as you like. As long as a model supports skills, you can use Ops Fleet with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ops Fleet AI skill free?

Yes. It is published on GitHub by Lifecycle-Innovations-Limited under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇