← Back to Skills Marketplace
ambition0802

ACP Background Runs

by sid · GitHub ↗ · v0.1.2 · MIT-0
cross-platform ✓ Security Clean
381
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install acp-background-runs
Description
Route requests for ACP or external coding agents such as Codex, Claude Code, Gemini CLI, and OpenCode into non-blocking OpenClaw background ACP runs instead...
README (SKILL.md)

ACP / Codex Background Runs

When a user asks to use ACP or an external coding agent such as Codex, Claude Code, Gemini CLI, or OpenCode, do not execute the task synchronously in the current chat. Route it through the ACP runtime instead.

Default Rules

  • Prefer sessions_spawn and set runtime: "acp" with the appropriate agentId
  • Default to mode: "run"
  • Only use thread: true or mode: "session" when the user explicitly asks for an ongoing interactive or thread-bound session
  • Set cwd when the target repository or directory is known
  • Prefer absolute paths for cwd; do not pass ~ directly, expand it first
  • Use a relaxed runTimeoutSeconds for longer tasks; do not mechanically default to 300
  • Do not wait in the current conversation and do not poll for progress
  • Reply immediately after submission that the task has been accepted and is running in the background
  • Rely on sessions_spawn completion notifications to send the final result back to the current conversation
  • Only add streamTo: "parent" when the user explicitly asks for progress updates

Default Handling

If the user is simply dispatching an ACP / Codex task and does not explicitly request a persistent interactive session, treat it as a one-shot background run. Do not block the current conversation. Send the result back only when the background run completes.

Timeout Guidance

  • Quick read-only checks, short analysis, light tasks: runTimeoutSeconds: 120-300
  • Normal coding tasks, project inspection, small scoped edits: runTimeoutSeconds: 600
  • Research, code changes, file generation, test runs, longer reports: runTimeoutSeconds: 1200
  • Clearly long-running tasks: increase further to 1800-3600 as needed
  • Do not default to 0; only use 0 when the user explicitly wants no timeout

mode / thread Decision Rules

  • If the user only wants the external agent to finish a task in the background, use mode: "run"
  • If the user explicitly wants to continue talking to the same external-agent context afterward, use thread: true
  • If the user explicitly asks for a persistent session, thread session, or long-lived context, use both thread: true and mode: "session"
  • If there is no explicit need for ongoing interaction, do not open mode: "session"

cwd Rules

  • If the target repository, project directory, or work directory is known, set cwd
  • Prefer absolute paths
  • Expand ~ before passing the path into sessions_spawn
  • If the user did not give a directory but the task clearly targets a known repo, resolve the actual path from context before spawning

Fallback When ACP Is Unavailable

  • Try runtime: "acp" first
  • Only fall back to runtime: "subagent" when the ACP target agentId is clearly unavailable, unconfigured, or ACP cannot be used in the current environment
  • When falling back, tell the user explicitly that the task is being run via subagent, not a native ACP session
  • Do not silently fall back

Reply After Submission

Use this short confirmation by default:

Task accepted. It is running in the background and will report back here when complete.

If streamTo: "parent" is enabled, also say that key progress updates will be streamed back.

Prohibited Actions

  • Do not execute external coding-agent tasks synchronously in the current conversation when they should go through ACP
  • Do not poll after submission
  • Do not call sessions_list, sessions_history, or similar tools to track child-session progress
  • Do not use sleep or timer-based waiting to fake background orchestration
  • Rely on the sessions_spawn completion / announce mechanism for the final result

Recommended Parameter Template

{
  "task": "\x3Cuser request>",
  "runtime": "acp",
  "agentId": "\x3Ccodex|claude|gemini|opencode|...>",
  "mode": "run",
  "cwd": "/abs/path/if-known",
  "runTimeoutSeconds": 300
}

When To Adjust

  • Need ongoing multi-turn context: add thread: true and, if needed, mode: "session"
  • Task may run for many minutes: increase runTimeoutSeconds
  • Task is only a quick read-only check: keep runTimeoutSeconds small
  • User explicitly wants progress relayed back: add streamTo: "parent"
  • ACP is unavailable but the task should still run in the background: explain the fallback and use runtime: "subagent"
Usage Guidance
This skill is internally consistent and doesn't ask for extra credentials or installs. Before enabling it, verify that: (1) your ACP/sessions_spawn infrastructure and agentIds (Codex, Claude, Gemini, etc.) are correctly configured and trusted; (2) background runs will only have access to repositories and filesystem paths you intend them to touch (the SKILL.md encourages setting cwd and resolving absolute paths); and (3) completion/notification mechanisms are enabled so results are returned to the conversation. If you have sensitive data in code/workspaces, test the skill on a non-sensitive repository or restrict agent filesystem permissions first.
Capability Analysis
Type: OpenClaw Skill Name: acp-background-runs Version: 0.1.2 The skill bundle provides instructions for an AI agent to delegate coding tasks to background sessions using the OpenClaw 'sessions_spawn' tool and 'acp' runtime. It defines logical routing rules for handling external agents like Codex or Claude Code, including timeout management and path expansion, without any evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
The skill's name and description match the instructions: it only describes how to spawn background ACP/subagent runs and sets parameters like runtime, agentId, mode, cwd, and timeouts. No unrelated binaries, secrets, or installs are requested.
Instruction Scope
Instructions stay on-topic (how to spawn background sessions, when to use run vs session/thread, timeouts, fallbacks). They do instruct the agent to set cwd and to resolve absolute paths from context, which is expected for code-work but means spawned background runs may access repository or filesystem paths — you should ensure filesystem access is limited to intended projects.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no environment variables, credentials, or config paths. It does not ask for unrelated secrets; the runtime parameters (agentId, runtime) are proportional to the stated purpose.
Persistence & Privilege
always is false and the skill allows normal autonomous invocation. It does not request permanent presence or modify other skills. Be aware that autonomous background runs will execute with whatever agent/session privileges are configured in your environment.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install acp-background-runs
  3. After installation, invoke the skill by name or use /acp-background-runs
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
Translate skill body to English and keep ACP background-run guidance intact
v0.1.1
Polish public description and trigger wording
v0.1.0
Initial publish
Metadata
Slug acp-background-runs
Version 0.1.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is ACP Background Runs?

Route requests for ACP or external coding agents such as Codex, Claude Code, Gemini CLI, and OpenCode into non-blocking OpenClaw background ACP runs instead... It is an AI Agent Skill for Claude Code / OpenClaw, with 381 downloads so far.

How do I install ACP Background Runs?

Run "/install acp-background-runs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ACP Background Runs free?

Yes, ACP Background Runs is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does ACP Background Runs support?

ACP Background Runs is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ACP Background Runs?

It is built and maintained by sid (@ambition0802); the current version is v0.1.2.

💬 Comments