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 Songhonglei/better-agent-skills --skill subagent-timeout-configgit clone --depth 1 https://github.com/Songhonglei/better-agent-skillsWrote 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/songhonglei/better-agent-skills/subagent-timeout-config)<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.
<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>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 | $0.00175 | $0.01595 |
| Opus 5.5 | $0.00070 | $0.00638 |
| Sonnet 5.5 | $0.00035 | $0.00319 |
| Haiku 4.5 | $0.00017 | $0.00160 |
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 1mo 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.
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
- Author: Evan Song · github.com/Songhonglei
- Repository: https://github.com/Songhonglei/better-agent-skills
- License: MIT
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 / fast → quick, slow → patient.
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)
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.
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.
- 1mo ago First seen · 180 lines · 175 tokens per session scan A a3485ef000ad
subagent-timeout-config is a skill published in the GitHub repository Songhonglei/better-agent-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 175 tokens to every session and 1,595 once invoked, about $0.0007 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
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.