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.
npx agentmods add skills/hmbown/codewhale/fleet-managernpx skills add Hmbown/CodeWhale --skill fleet-managergit clone --depth 1 https://github.com/Hmbown/CodeWhaleWrote 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.
[](https://agentmods.dev/skills/hmbown/codewhale/fleet-manager)<a href="https://agentmods.dev/skills/hmbown/codewhale/fleet-manager"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/fleet-manager.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00025 | $0.00985 |
| Opus 5 | $0.00013 | $0.00492 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
fleet-manager 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pod Manager
Use this skill when acting as a manager agent for Codewhale Pod 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 Pod surfaces over shell spelunking:
codewhale pod status,inspect,logs,artifacts,interrupt,restart,stop, 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
- Identify the run and worker from the user request, run receipt, or Pod
status output. If no worker is named, start with
codewhale pod status. - Inspect the worker with
codewhale pod inspect <worker-id>or the matching Runtime API worker endpoint. - Review bounded evidence with
codewhale pod logs <worker-id>andcodewhale pod artifacts <worker-id>. Summarize artifact refs, not full payloads. - 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.
- Choose one typed action:
- transient and retry budget remains:
codewhale pod 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.
- transient and retry budget remains:
- Record the result in the response: classification, action taken or drafted, evidence commands, artifact refs, and next owner.
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.
- 2d ago Changed · -1 tokens per session ffb4af1ea509
- 4d ago First seen · 107 lines · 26 tokens per session scan A 3a7830613a1b
fleet-manager is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 985 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
claw-orchestrator
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel…
ultraapp-interview
Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
visual-acceptance
UI/视觉改动交付前的终验方法论——多主题截图矩阵复现、像素真值判据链、CSS 层叠陷阱、布局漂移审查、before/after 存证。当视觉改动需要验收（而非实现）时使用：交付前最后一环，回答「看得见的部分真的对吗」。.
code-review
Run a thorough self-review pass on the most recent change.
design-prototype
Frontend UI prototype workflow — clarify intent, explore directions, preview across viewports, diff against references, deliver with screenshot evidence.