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 skills add cyuanxv/agent-cockpit --skill manage-task-workspacesgit clone --depth 1 https://github.com/cyuanxv/agent-cockpitWrote 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/cyuanxv/agent-cockpit/manage-task-workspaces)<a href="https://agentmods.dev/skills/cyuanxv/agent-cockpit/manage-task-workspaces"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/manage-task-workspaces/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.
<a href="https://agentmods.dev/skills/cyuanxv/agent-cockpit/manage-task-workspaces"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/manage-task-workspaces.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00067 | $0.00751 |
| Opus 5.5 | $0.00027 | $0.00300 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
manage-task-workspaces 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 2mo 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.
What it actually says
管理任务 Worktree
适用规则
- 只读盘点不创建 Worktree；第一次写入前创建。
- 使用安装后的
cockpit命令，不手工拼接多仓库 Worktree。 - 每个仓库只提交明确列出的相对路径。
finish、外部推送、PR、合并和cleanup都保留独立门禁。- 状态真相在规范仓根的
.cockpit-runs/task-workspaces/<task-id>/state.json。
遇到失败、部分推送、PR 已合并但状态滞后或清理拒绝时，读取 references/recovery.md。
标准流程
-
检查环境和仓库配置：
cockpit --root <workspace-root> doctor cockpit --root <workspace-root> repos -
创建任务空间；根仓自动加入，其它仓库显式指定：
cockpit --root <workspace-root> start <task-id> --repo <repo-key>mount_path必须已经被根仓.gitignore忽略。不要把原 dirty 目录的 未提交文件搬进任务空间。 -
在输出的 workspace 内工作。需要切换客户端时，只打印启动命令：
cockpit --root <workspace-root> launch <task-id> --runtime <runtime-key> -
每个仓库单独检查或提交：
cockpit --root <workspace-root> prepare <task-id> \ --repo <repo-key> \ --path <relative-path> \ --message "<commit message>"提交语言和格式由
.cockpit/config.json的commit_message_pattern决定；未配置时不限制语言。 -
收尾前先展示无副作用计划：
cockpit --root <workspace-root> finish <task-id> --dry-run -
只有用户明确授权外部集成后，才传配置中的确认短语：
cockpit --root <workspace-root> finish <task-id> --confirm <phrase>默认短语是
integrate。必须逐仓遵守manual、local_only、pull_request或direct_main策略，不能临时降级安全门禁。 -
清理是单独动作，先预览再确认：
cockpit --root <workspace-root> cleanup <task-id> --dry-run cockpit --root <workspace-root> cleanup <task-id> --confirm cleanup清理只移除符合条件的干净 Worktree，保留任务分支和审计状态；不提供
--force。
报告内容
向用户报告任务 workspace、任务分支、各仓库阶段、实际验证、未验证边界和 下一步。没有后续动作时明确写“任务完结”。
What ships with it
8 files 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.
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.
- 2mo ago First seen · 85 lines · 67 tokens per session scan A 4fa9a8c6c5e7
manage-task-workspaces is a skill published in the GitHub repository cyuanxv/agent-cockpit (2 stars, last pushed 25d ago), licensed MIT. It adds 67 tokens to every session and 751 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
work
Handle issue/PR work items with worktree isolation. Triggered by "/work [issuelink|description]" to start focused work.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
meta-issue-to-pr-autopilot
Triages an issue, delegates the fix to sub-agent, drafts a PR description with summarize, and opens the PR via gh. Best used on small, well-scoped issues with clear acceptance criteria.
omh-github-issue-intake
This is an OMH github-issue-intake workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
meta-github-pr-watch-digest
Inspect the user's open GitHub PRs / failing CI / new issues via gh, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.