Skip to content
Agentmart
Submit a tool

long-running-tasks

Manage long-running commands and multi-step work in Codex.

Skill by jajupmochi

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jajupmochi-long-running-tasks

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Manage long-running commands and multi-step work in Codex. Use when a task may exceed normal turn time, needs a dev server, watcher, training run, crawl, benchmark, or repeated polling.

Use cases: backend, productivity, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/long-running-tasks

What's inside

Skill name
long-running-tasks
Description
Manage long-running commands and multi-step work in Codex. Use when a task may exceed normal turn time, needs a dev server, watcher, training run, crawl, benchmark, or repeated polling.
License
MIT
Instructions
23 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# long-running-tasks

Read `../general/long-running-tasks/SKILL.md` for the original policy, then use
these Codex mappings:

- Claude background Bash -> Codex background `exec_command` session.
- Claude Monitor -> periodic `write_stdin` polling or explicit status command.
- Claude subagent -> Codex subagent only if available and useful; otherwise use
  a focused plan and background terminal.
- Claude "ask before long run" -> Codex approval when the run needs network,
  writes outside the workspace, high cost, or destructive side effects.

Workflow:

1. Estimate duration and side effects.
2. For commands expected to run longer than a normal tool call, start them in a
   background session and keep the session id.
3. Poll at reasonable intervals. Do not spam the transcript with full logs.
4. Stop or clean up sessions that are no longer needed before final response.
5. If a task is too large for one run, leave a concrete continuation state:
   current command, session id, last observed output, and next check.

From jajupmochi/agent-harness, MIT.

More from jajupmochi/agent-harness

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 8, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/jajupmochi/agent-harness
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from jajupmochi

Cite this page

long-running-tasks skill. Agent Mart. https://agentmart.dev/skills/jajupmochi-long-running-tasks (last updated 2026-10-24)