Skip to content
Skills Library
AI & agents · Automation

agent-stop

/agent-stop

Use when stopping OMH tmux agents or cleaning their worktrees and branches safely.

Licence
MIT
Last repository change
28.07.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 28.07.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when stopping OMH tmux agents or cleaning their worktrees and branches safely.

Original author description

Use when stopping OMH tmux agents or cleaning their worktrees and branches safely.

How it works

SKILL.md has no level-two headings · 37 lines, 312 words

SKILL.md preview
---
name: agent-stop
description: Use when stopping OMH tmux agents or cleaning their worktrees and branches safely.
---

# Stop and clean up agents

Read and validate `.claude/.omh/agents.json`. Resolve the requested recorded ids (default all), tmux
session, worktrees, branches, base branch, and `useWorktree`.

Inspect pane liveness, uncommitted files, and unmerged commits for every target. Show exactly what
would be interrupted, which worktree/branch would be removed, and what work would become
unreachable. Obtain explicit confirmation before shutdown or cleanup even when no unmerged work is
detected.

When unmerged or uncommitted work exists, require one explicit choice per target:

- `apply`: stop and invoke `/agent-apply` behavior before later cleanup;
- `keep`: stop the process but preserve branch, worktree, and state;
- `discard`: authorize the named unmerged commits/files and exact cleanup targets;
- `cancel`: do nothing.

Never infer discard from a generic “stop.” Interrupt only the confirmed panes. After each
interrupt attempt, atomically persist the interrupt result and timestamp in `agents.json`, then
recheck tmux pane and underlying process liveness. User confirmation or a sent interrupt is not
proof of termination. Mark an agent stopped only after observed termination. Kill the tmux session
only after every recorded pane and process is observed terminal.

With `useWorktree: true`, remove only validated, recorded worktree paths after observed termination.
Restore any protected `TASK.md` backup and verify its recorded hash before apply or cleanup. Use
forced removal or branch deletion only after the explicit `discard` authorization named that
target. With `useWorktree: false`, do not run branch or worktree cleanup.

Atomically update `.claude/.omh/agents.json`: preserve kept resources and partial-stop entries; set
stopped status when resources remain. Remove the state file only after all agents are stopped and
all recorded resources are either cleaned with confirmation or deliberately preserved elsewhere.
On a failed or partial stop, retain state and resources, record the last observed liveness, and
report recovery commands such as `tmux attach -t "<session>"`, `/agent-status`, and
`/agent-stop <id>`. Report what was stopped, kept, removed, and whether removed work can be
recovered.

Versions

The database has no other skills named agent-stop.

Database snapshot: 13.11.2026 · package version 701e543797ce (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 91agent-status
    Use when inspecting tmux agent liveness, commits, diffs, and shared OMH agent state.
  • 86team-stop
    Use when interrupting a Codex native subagent team or cleaning its shared OMH state.
  • 100omh
    Generate oh-my-hi dashboard. Visual catalog and usage/token analysis across Claude Code & Codex — skills, agents, plugins, hooks, memory, MCP servers, rules, and principles. Triggered by "/omh", "harness status", "dashboard", etc.
  • 100tmux-agent-comms
    Manage AI agents in tmux: spawn sessions, send messages, wait, capture replies, inspect fleets, and tear down safely. Use for tmux-hosted CLI agents. Don't use for SSH, GNU screen, or GUI apps.
  • 100workmux
    Manage terminal agents, git worktrees, and tmux sessions with workmux. Use when the user asks to open or start an agent in a project, check running agents or their progress in a tmux session, or work with workmux, worktrees, or parallel agent workflows.
  • 100agent-manager
    tmux + Python agent lifecycle manager — start, stop, monitor, and assign tasks to AI agents running in tmux sessions. Use when managing multiple AI agents without a server, scheduling agent jobs via cron, monitoring agent heartbeats, or injecting skills into agent sessions. Zero…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.