subagent-timeout-config

subagent-timeout-config is a skill for Claude Code, Codex from Songhonglei/better-agent-skills. It costs 175 tokens per session (1,595 once invoked), scanned A, original, MIT.

A configurator for three related OpenClaw subagent timeout settings. A subagent is a helper agent running a task, and these settings control call limits, task duration, and session lifetime.

In plain words
What is it for?
Use it to apply quick, standard, or extended timeout profiles, or set a different JSON configuration file with the --config option.
Why use it?
It prevents mismatched limits that can end a session before a helper agent finishes. It updates the settings together, validates their time relationship, and can make a backup before an optional restart.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions subagents; mentions Codex; built for openclaw.

Good fit Use it to apply quick, standard, or extended timeout profiles, or set a different JSON configuration file with the --config option.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/songhonglei/better-agent-skills/subagent-timeout-config
Install

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.

Any agent
npx skills add Songhonglei/better-agent-skills --skill subagent-timeout-config
Clone the repo
git clone --depth 1 https://github.com/Songhonglei/better-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for subagent-timeout-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/subagent-timeout-config/github.svg)](https://agentmods.dev/skills/songhonglei/better-agent-skills/subagent-timeout-config)
Your own site
<a href="https://agentmods.dev/skills/songhonglei/better-agent-skills/subagent-timeout-config"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/subagent-timeout-config/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.

agentmods 80×15 button for subagent-timeout-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/songhonglei/better-agent-skills/subagent-timeout-config"><img src="https://agentmods.dev/badge/skills/songhonglei/better-agent-skills/subagent-timeout-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00175 $0.01595
Opus 5 $0.00088 $0.00797
Sonnet 5 $0.00035 $0.00319
Haiku 4.5 $0.00017 $0.00160

Measured 10d ago against content hash a3485ef000ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

subagent-timeout-config 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/set_timeout.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/subagent-timeout-config/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

subagent-timeout-config

One-click timeout configurator for OpenClaw subagents. Set the three related timeout fields atomically with built-in constraint validation, automatic backup, and optional gateway restart.

⚠️ OpenClaw-only by default — reads/writes ~/.openclaw/openclaw.json. Use --config <path> to target a different runtime's JSON config file.


Why this skill exists

OpenClaw timeouts are split across three nested fields that must be tuned together:

Field Path What it controls
timeoutSeconds agents.defaults.timeoutSeconds Per-tool-call wait
runTimeoutSeconds agents.defaults.subagents.runTimeoutSeconds Per-subagent task budget
ttlMinutes acp.runtime.ttlMinutes ACP session lifetime

Hidden trap: ttlMinutes * 60 must be ≥ runTimeoutSeconds, otherwise sessions die before subagents finish. Default OpenClaw values (30s / 30min / 30min) are too tight for many real-world tasks (codex/claude-code planning, large refactors, complex analysis).

This skill picks the right combination in one command, validates the constraint, backs up the original config, and restarts the gateway.


Preset Profiles

Profile timeoutSeconds runTimeoutSeconds ttlMinutes Use case
quick 60s (1min) 3600s (1h) 60min (1h) Fast feedback, interactive debugging
normal 180s (3min) 7200s (2h) 120min (2h) Everyday development
patient 300s (5min) 10800s (3h) 180min (3h) Long-running tasks, big codebases

Aliases: impatient / fastquick, slowpatient.


Usage

Preview before applying (recommended first time)

python3 <skill-install-path>/scripts/set_timeout.py --profile normal --dry-run

Apply a profile (with auto-restart)

Read the full file on GitHub · 180 lines

Files

What ships with it

4 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.

Changes

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.

  1. 10d ago First seen · 180 lines · 175 tokens per session scan A a3485ef000ad

Subscribe to this mod's changes

subagent-timeout-config is a skill published in the GitHub repository Songhonglei/better-agent-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 175 tokens to every session and 1,595 once invoked, about $0.0009 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 2026-08-31.