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

Codewhale Fleet Manager

by codewhale-hq in codewhale-hq/Codewhale

Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

MITAuto-check passedAgent Workflows

Install Codewhale Fleet Manager

skills CLI
$ npx skills add codewhale-hq/Codewhale --skill fleet-manager -a claude-code

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

GitHub CLI
$ gh skill install codewhale-hq/Codewhale fleet-manager --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/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/tui/assets/skills/fleet-manager .claude/skills/fleet-manager && 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-manager
GitHub stars
41k
Token cost
~1.2k tokens
SKILL.md length
513 words
Files
1
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

  • Works in 6 steps: Identify the run and worker from the… → Inspect the worker with codewhale fleet… → Review bounded evidence with codewhale… → …
  • Checking on a stalled or failed Codewhale worker
  • SKILL.md covers Authority Boundary, Triage Loop, Restart vs Escalate and Safe Escalation Draft, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill is for a manager agent supervising Codewhale fleet runs. It prefers typed fleet commands such as `codewhale fleet status`, `inspect`, `logs`, `artifacts`, `interrupt`, `restart`, `resume` and `stop`, along with the matching Runtime API endpoints, over reading fleet files or host logs directly. It does not send Slack, webhook, PagerDuty, email or chat messages unless explicitly authorized, drafting them instead, and it keeps secrets, tokens and oversized logs out of summaries.

The triage loop identifies the run and worker, inspects it, reviews bounded logs and artifact references, and classifies the state as a transient failure, task failure, verifier failure or needs-human. It then picks one action: resume a run with orphaned leases after a manager restart, restart a worker when the failure is transient and retry budget remains, or draft an escalation and mark needs-human when a retry is unsafe. For task failures it preserves artifacts and summarizes the failure. The result is a ledgered receipt or a safe escalation draft.

When your agent uses it

  • Checking on a stalled or failed Codewhale worker
  • Deciding whether to restart, resume or escalate a worker
  • Writing a safe summary or escalation draft for a failed run

Example prompts

  • “Check the status of the current fleet run and tell me which workers need attention.”
  • “Inspect this worker's logs and decide whether it should be restarted.”
  • “Draft an escalation for the run that keeps failing verification, without including any secrets.”

Requirements

  • The `codewhale` CLI with access to the fleet's Runtime API

Workflow steps

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

  1. Identify the run and worker from the user request, run receipt, or fleet
  2. Inspect the worker with codewhale fleet inspect or the
  3. Review bounded evidence with codewhale fleet logs and
  4. Classify the state before acting
  5. Choose one typed action
  6. Record the result in the response: classification, action taken or drafted,

What it can do on your machine

Read from SKILL.md and the folder at commit 8d2fb45. 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.

    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

Codewhale Fleet Manager loads about 1.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 513 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 codewhale-hq/Codewhale at commit 8d2fb45, republished under its MIT licence (© codewhale-hq). 513 words, ~1,197 tokens.

Download SKILL.mdSave it as .claude/skills/fleet-manager/SKILL.md (or your agent's skills folder).
name
fleet-manager
description
Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers.
metadata.short-description
Triage Codewhale fleet runs

Fleet Manager

Use this skill when acting as a manager agent for Codewhale fleet runs. Your job is to classify worker state, choose the narrowest safe typed action, and leave a ledgered receipt or a safe escalation draft.

Authority Boundary

  • Prefer typed fleet surfaces over shell spelunking: codewhale fleet status, inspect, logs, artifacts, interrupt, restart, resume, stop (stop requires --all), and the Runtime API endpoints.
  • Do not read .codewhale/fleet.jsonl, host logs, or remote files directly unless the typed command or API is missing required evidence.
  • Do not send Slack, webhook, PagerDuty, email, or chat messages unless the user or run config explicitly authorizes sending. Draft the message instead.
  • Never include secrets, tokens, webhook URLs, routing keys, full prompts, or oversized logs in a summary or escalation.

Triage Loop

  1. Identify the run and worker from the user request, run receipt, or fleet status output. If no worker is named, start with codewhale fleet status.
  2. Inspect the worker with codewhale fleet inspect <worker-id> or the matching Runtime API worker endpoint (GET /v1/fleet/workers/{worker_id}).
  3. Review bounded evidence with codewhale fleet logs <worker-id> and codewhale fleet artifacts <worker-id>, or the Runtime API equivalents (GET /v1/fleet/runs/{run_id}/receipts/{task_id}/evidence and GET /v1/fleet/runs/{run_id}/events/replay). Summarize artifact refs, not full payloads.
  4. Classify the state before acting:
    • transient failure: transport error, timeout, stale heartbeat, host unavailable, or retryable provider/network failure.
    • task failure: worker completed the task but the result is wrong, missing required artifacts, or reports a domain error.
    • verifier failure: scorer/verifier failed or disagrees with the worker result.
    • needs-human: missing authority, unsafe secret boundary, destructive action, repeated restart exhaustion, ambiguous product decision, or conflict between artifacts and verifier.
  5. Choose one typed action:
    • run has orphaned leases after a manager restart: codewhale fleet resume <run-id> (idempotent reconcile).
    • transient and retry budget remains: codewhale fleet restart <worker-id>.
    • transient but unsafe to retry: draft escalation and mark needs-human.
    • task failure: preserve artifacts, summarize the failure, and avoid restart unless the task spec says retrying can produce new evidence.
    • verifier failure: inspect scorer inputs and artifacts, then escalate if the verifier cannot be corrected through a typed action.
    • needs-human: do not restart automatically; draft a concise escalation.
  6. Record the result in the response: classification, action taken or drafted, evidence commands, artifact refs, and next owner.
Show full SKILL.md (138 more words)Show less

Restart vs Escalate

Restart only when all of these are true:

  • the failure is likely transient,
  • the task is idempotent or the run policy allows retry,
  • retry budget remains,
  • no secret, permission, or destructive action boundary is involved, and
  • the previous attempt produced enough receipt data to explain the restart.

Escalate when any of these are true:

  • restart budget is exhausted,
  • the worker requests secrets or new authority,
  • artifacts indicate data loss, corruption, or destructive side effects,
  • the verifier and task result conflict in a way you cannot resolve from typed evidence,
  • the same failure repeats after a restart, or
  • a human product or release decision is required.

Safe Escalation Draft

Use this shape for Slack/PagerDuty drafts. Keep logs to three short lines or an artifact ref.

text
Codewhale fleet needs attention
Run: <run-id>
Worker: <worker-id>
Task: <task-id or unknown>
Classification: <transient failure | task failure | verifier failure | needs-human>
Reason: <one sentence, no secrets>
Latest typed evidence: codewhale fleet inspect <worker-id>; codewhale fleet artifacts <worker-id>
Safe log excerpt: <3 lines max or "see artifact <ref>">
Requested decision: <restart approval | verifier review | task owner review | permission decision>

Post-Run Receipt

End every Fleet Manager response with a compact receipt:

text
Fleet receipt
Run: <run-id>
Workers checked: <count/list>
Classification: <state>
Action: <restart/interrupt/stop/resume/escalation draft/no-op>
Ledger expectation: <typed action should be recorded | draft only, no send>
Artifacts reviewed: <refs>
Follow-up owner: <manager | task owner | human>

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

Files

Just SKILL.md in crates/tui/assets/skills/fleet-manager of codewhale-hq/Codewhale.

Open the folder on GitHubat commit 8d2fb45

Compare with similar skills

Codewhale Fleet Manager 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.

Codewhale Fleet Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codewhale Fleet Manager this skillcodewhale-hq/Codewhale41k—~1.2kAutomated safety check: PassMIT
Fleet Manager for Agent Sessionsasgeirtj/system_prompts_leaks69k—~2.5kAutomated safety check: PassCC0-1.0
Adk Agent Buildergoogle/adk-python22k—~879Automated safety check: PassApache-2.0
cmux Cloud Machinesmanaflow-ai/cmux28k—~864Automated safety check: PassCustom licence
Smithers Durable Flow Driversmithersai/smithers430—~3kAutomated safety check: PassMIT
Sol and Luna Worker Routermajiayu000/spellbook287—~3.3kAutomated safety check: PassMIT

Similar skills

  • Fleet Manager for Agent Sessions

    asgeirtj/system_prompts_leaks

    Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

    69k GitHub stars~2.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Adk Agent Builder

    google/adk-python

    Official

    Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between…

    22k GitHub stars~879 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • cmux Cloud Machines

    manaflow-ai/cmux

    Operates cmux Cloud machines from the cmux CLI, running durable remote commands or detached agents and presenting their workspaces, with authorization limits on destructive steps.

    28k GitHub stars~864 tokensUpdated today
    DevOps & CloudAuto-check passed

  • Smithers Durable Flow Driver

    smithersai/smithers

    Runs or authors Smithers TypeScript flows for ordered agent stages with retries, approvals, bounded loops and crash-safe recovery, built from Flow.make, Action.make and Effect.

    430 GitHub stars~3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Sol and Luna Worker Router

    majiayu000/spellbook

    Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

    287 GitHub stars~3.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Council External Codex Review

    affaan-m/ECC

    Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent.

    276k GitHub stars~1.5k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from codewhale-hq/Codewhale

All 63 skills in this repo

  • Codewhale Dogfood Install

    codewhale-hq/Codewhale

    Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Codewhale Session Handoff

    codewhale-hq/Codewhale

    Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

    41k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Codewhale Landing Workflow

    codewhale-hq/Codewhale

    Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.

    41k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Auto-check passed

  • GitHub Issue Bulk Assigner

    codewhale-hq/Codewhale

    Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.

    41k GitHub stars~953 tokensUpdated today
    Auto-check passed

  • Codewhale Issue Filing

    codewhale-hq/Codewhale

    Turns a bug or idea into a single actionable Codewhale GitHub issue with evidence, a gap-naming title, acceptance criteria and related links.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Codewhale Fleet Manager

What does Codewhale Fleet Manager do?

Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation. The skill is for a manager agent supervising Codewhale fleet runs. It prefers typed fleet commands such as `codewhale fleet status`, `inspect`, `logs`, `artifacts`, `interrupt`, `restart`, `resume` and `stop`, along with the matching Runtime API endpoints, over reading fleet files or host logs directly.

When should I use Codewhale Fleet Manager?

Codewhale Fleet Manager fits situations like: checking on a stalled or failed Codewhale worker; deciding whether to restart, resume or escalate a worker; writing a safe summary or escalation draft for a failed run.

How do I install Codewhale Fleet Manager in Claude Code?

Run `npx skills add codewhale-hq/Codewhale --skill fleet-manager -a claude-code`. Or copy the skill folder (crates/tui/assets/skills/fleet-manager in codewhale-hq/Codewhale) into .claude/skills/fleet-manager in your project. Claude Code loads it when a task matches its description.

How do I install Codewhale Fleet Manager in Codex?

Run `npx skills add codewhale-hq/Codewhale --skill fleet-manager -a codex`. Or copy the skill folder (crates/tui/assets/skills/fleet-manager in codewhale-hq/Codewhale) into .agents/skills/fleet-manager in your project. Codex loads it when a task matches its description.

Can I use Codewhale Fleet Manager 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 codewhale-hq/Codewhale --skill fleet-manager -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-manager, .gemini/skills/fleet-manager, .github/skills/fleet-manager and .opencode/skills/fleet-manager in your project.

What does Codewhale Fleet Manager need to run?

SKILL.md names no scripts, command-line tools or credentials: Codewhale Fleet Manager is instructions for the agent only. Our summary lists: The `codewhale` CLI with access to the fleet's Runtime API.

Does Codewhale Fleet Manager 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 Codewhale Fleet Manager 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 Codewhale Fleet Manager use?

Codewhale Fleet Manager 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 Codewhale Fleet Manager use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codewhale Fleet Manager?

Skills that share tags, products or a category with Codewhale Fleet Manager: Fleet Manager for Agent Sessions (asgeirtj/system_prompts_leaks, 69k stars), Adk Agent Builder (google/adk-python, 22k stars), cmux Cloud Machines (manaflow-ai/cmux, 28k stars) and Smithers Durable Flow Driver (smithersai/smithers, 430 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codewhale Fleet Manager?

codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,078 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.

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