Files
.tweakcc/system-prompts/tool-description-task.md
wassname 5801e299d5 Phase 2: version conflicts, hooks, compression (+108 -179)
- Resolve 8 upstream version conflicts (bump ccVersions to 2.1.63)
- Merge askuserquestion "don't reference the plan" guidance from v2.1.47
- Move git guardrails to hooks: --no-verify, broad staging, interactive mode
- Gut redundant prompt sub-files (destructive-ops, skip-hooks, sleep, computer)
- Compress 10 system-prompt files 56% (1529w -> 672w)
- Improve context compaction summary to preserve decision path
- Update CLAUDE.md: fix principles, add Southbridge-sourced loading model

Always-loaded: ~7.5k words (down from ~10.8k stock, ~31% total reduction)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 15:35:01 +08:00

1.3 KiB

${TASK_TOOL_PREAMBLE}

When NOT to use: for specific file reads (use ${READ_TOOL}/${GLOB_TOOL}), searching 2-3 files, or tasks unrelated to agent descriptions.

Usage:

  • Short description (3-5 words) per agent${GET_SUBSCRIPTION_TYPE_FN()!=="pro"?`
  • Launch multiple agents concurrently in a single message:""}${!IS_TRUTHY_FN(PROCESS_OBJECT.env.CLAUDE_CODE_DISABLE_BACKGROUND_TASKS)&&!FALSE()?
  • run_in_background: you will be notified on completion — do NOT sleep, poll, or proactively check`:""}
  • Agent results are not visible to user; summarize them in text
  • resume: pass agent ID to continue previous context
  • isolation: "worktree" for isolated repo copy (auto-cleaned if no changes)
  • Tell agents whether to write code or just research
  • If agent should be used proactively per its description, do so
  • Parallel: multiple ${TASK_TOOL_OBJECT.name} calls in one message${FALSE()?`
  • run_in_background, name, team_name, mode not available here`:""}