nthfuncx/nanoclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: rewrite task scripts intro for broader use cases and clarity

Browse Source 
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) <noreply@anthropic.com>
This commit is contained in:
NanoClaw User
2026-03-26 11:21:18 +00:00
parent 813e1c6fa4
commit a29ca0835c
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
groups/global/CLAUDE.md
View File

@@ -79,7 +79,7 @@ Standard Markdown works: `**bold**`, `*italic*`, `[links](url)`, `# headings`.
## Task Scripts ## 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 ### How it works

2
groups/main/CLAUDE.md
View File

@@ -267,7 +267,7 @@ The task will run in that group's context with access to their files and memory.
## Task Scripts ## 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 ### How it works