Source instructions onlyA profile for deciding exactly what context each subagent should receive and what to leave out.

Install or setup path

Follow the upstream source for installation instructions.

No verified install command on this page

This profile is useful for evaluation and workflow context, but WhichAITools did not verify one direct install command for it. Use the linked source instructions instead of guessing.

Source instructions

Use this profile for

Operators and prompt authors refining subagent prompts, handoffs, and delegation quality in Claude Code workflows.

Primary categoryClaude Code Workflows
Source count1
OpenClaw relevantNo

What it does

This profile focuses on context design for subagents: which files, instructions, constraints, and goals to pass down so the delegated task is informed but not overloaded. It helps teams improve subagent quality by treating context as a deliberate design choice rather than dumping the entire main-thread state into every worker.

Best for

Operators and prompt authors refining subagent prompts, handoffs, and delegation quality in Claude Code workflows.

Why it stands out

It tackles one of the hardest subagent problems directly: giving enough context to be useful without destroying focus.

Adopt this skill carefully

Return to the parent path

Move back to the category or hub instead of jumping to the homepage and losing context.

Cross-check the method

Review methodology and manuals before treating a public profile or copied command like production-ready guidance.

Use the surrounding workflow hub

When the profile belongs to OpenClaw operations, continue inside the OpenClaw cluster instead of starting over.

Safety notes

  • Do not pass broad repo or secret context to every subagent by default; include only what the delegated task truly needs.
  • If a subagent can run shell commands or edit files, scope both the context and permission boundary together so they reinforce each other.
  • Re-check context packages when delegated tasks fail, because both too much and too little context can cause misleading output.

Source context

从 SkillsMP 发现的 skill,autoScore 6/10。需要人工审查后方可升级至 bruce-tested。

scoping-context-for-subagents on SkillsMP

Related profiles

Subagents Workflow

Use this profile when one Claude Code session is becoming a bottleneck and the work can be split into parallel, scoped subtasks with cleaner context boundaries.

subagent-testing

Use this profile when you are authoring or refining subagent workflows and need a repeatable way to verify them. It is useful for teams that treat subagents as reusable operational units rather than one-off experiments.

Prompt Engineering Skill

Use this profile when the quality bottleneck is not installation but instruction design: project rules, system framing, few-shot examples, and stable prompt patterns that Claude Code can reuse.