From a29ca0835c37ede7ef490e21dda6a6a840bbe4a7 Mon Sep 17 00:00:00 2001 From: NanoClaw User Date: Thu, 26 Mar 2026 11:21:18 +0000 Subject: [PATCH] fix: rewrite task scripts intro for broader use cases and clarity Broadens the trigger from "check or monitor" to "any recurring task", adds context about API credit usage and account risk for frequent tasks, and prompts the agent to clarify ambiguous requests. Co-Authored-By: Claude Opus 4.6 (1M context) --- groups/global/CLAUDE.md | 2 +- groups/main/CLAUDE.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/groups/global/CLAUDE.md b/groups/global/CLAUDE.md index 7018c04..935578a 100644 --- a/groups/global/CLAUDE.md +++ b/groups/global/CLAUDE.md @@ -79,7 +79,7 @@ Standard Markdown works: `**bold**`, `*italic*`, `[links](url)`, `# headings`. ## Task Scripts -To check or monitor something on a recurring basis, use `schedule_task` — not a bash loop. This way the check survives container restarts and doesn't block other messages. If the user only needs to know when a condition changes, add a `script` to avoid unnecessary wake-ups — the script runs first, and you only wake up when there's something to act on. +For any recurring task, use `schedule_task`. Tasks that wake the agent frequently — especially multiple times a day — consume API credits and can risk account restrictions. If a simple check can determine whether you need to act, add a `script` — it runs first, and you only wake up when the check passes. This keeps agent invocations to a minimum. If it's unclear whether the user wants a response every time or only when something requires attention, ask. ### How it works diff --git a/groups/main/CLAUDE.md b/groups/main/CLAUDE.md index 5e693fa..d3ea5f9 100644 --- a/groups/main/CLAUDE.md +++ b/groups/main/CLAUDE.md @@ -267,7 +267,7 @@ The task will run in that group's context with access to their files and memory. ## Task Scripts -To check or monitor something on a recurring basis, use `schedule_task` — not a bash loop. This way the check survives container restarts and doesn't block other messages. If the user only needs to know when a condition changes, add a `script` to avoid unnecessary wake-ups — the script runs first, and you only wake up when there's something to act on. +For any recurring task, use `schedule_task`. Tasks that wake the agent frequently — especially multiple times a day — consume API credits and can risk account restrictions. If a simple check can determine whether you need to act, add a `script` — it runs first, and you only wake up when the check passes. This keeps agent invocations to a minimum. If it's unclear whether the user wants a response every time or only when something requires attention, ask. ### How it works