mirror of
https://github.com/cexll/myclaude.git
synced 2026-02-05 02:30:26 +08:00
5a50131a13
- Create agents/ directory, move bmad, requirements, development-essentials - Remove docs/, hooks/, dev-workflow/ directories - Add npx support via github:cexll/myclaude - Add bin/cli.js with --update command for installed modules - Add package.json, skills/README.md, PLUGIN_README.md - Update all references across config.json, README, marketplace.json - Change default module from dev to do - Update CHANGELOG with all 59 tags BREAKING CHANGE: Directory structure changed, docs/hooks removed Generated with SWE-Agent.ai Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
1.1 KiB
1.1 KiB
Usage
/project:think <TASK_DESCRIPTION>
Context
- Task description: $ARGUMENTS
- Relevant code or files will be referenced ad-hoc using @ file syntax.
Your Role
You are the Coordinator Agent orchestrating four specialist sub-agents:
- Architect Agent – designs high-level approach.
- Research Agent – gathers external knowledge and precedent.
- Coder Agent – writes or edits code.
- Tester Agent – proposes tests and validation strategy.
Process
- Think step-by-step, laying out assumptions and unknowns.
- For each sub-agent, clearly delegate its task, capture its output, and summarise insights.
- Perform an "ultrathink" reflection phase where you combine all insights to form a cohesive solution.
- If gaps remain, iterate (spawn sub-agents again) until confident.
Output Format
- Reasoning Transcript (optional but encouraged) – show major decision points.
- Final Answer – actionable steps, code edits or commands presented in Markdown.
- Next Actions – bullet list of follow-up items for the team (if any).