escoffier-labs/brigade/ultra-work-scout
Claude Code and agent skill by escoffier-labs/brigade
- community
Checking that the SKILL.md file is still in the repository.
Use when the user asks for ultra work, scout work, broad pre-implementation scouting, or parallel investigation before a large Brigade task. Designed for Codex and other SKILL.md harnesses that can delegate or split work.
Install
npx vskill@latest install escoffier-labs/brigade/ultra-work-scoutSKILL.md
ultra-work-scout
Use this skill when a task is important enough to scout before changing code, especially when the user asks for "ultra work", "scout this", "use scouts", "use subagents", or "really scope this out".
Mission
Turn a large request into a small number of parallel, bounded scouting jobs, then bring the results back into one implementation path. Scouts gather context and risks; they do not replace the main agent's ownership of the final change.
Default Scout Set
Start with the smallest set that can answer independent questions:
- Surface scout: find the public commands, docs, templates, and user-facing entry points that must change.
- Install scout: trace init, upgrade, profile, and default-install paths so new users get the intended behavior.
- Verification scout: identify focused tests, full checks, and existing flaky or environment-sensitive gates.
Only add more scouts when the work naturally splits into independent repos or subsystems.
Main Agent Loop
- State the immediate local task you will keep yourself.
- Assign scouts concrete questions with disjoint read or write scopes.
- Keep moving on non-overlapping work while scouts run.
- Integrate only findings you can verify in the current tree.
- Run verification through Brigade:
If --capture is not available in the installed Brigade version, run:
Boundaries
- Do not spawn scouts for tiny, single-file fixes.
- Do not let scouts mutate the same files unless you explicitly split ownership.
- Do not trust a scout's success claim without reading the diff or output that matters.
- Do not skip the final Brigade verify and outcome capture.
Output Contract
Finish with:
- Scout questions asked and what changed because of them.
- Files changed.
- Verification command and result.
- Any release blocker or follow-up that remains.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsrc/brigade/templates/skills/ultra-work-scout/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/escoffier-labs/brigade/ultra-work-scout)