benchmark
Run SWE-bench Lite benchmarks against agtx coding agent workflows. Guides setup, configuration, execution, evaluation, and…
Enter brainstorm mode to explore a feature or enhancement idea. Stays in discussion mode only — no planning, no implementation. Use /agtx:sweep when ready to push outcomes to the board.
Claude Code
$ npx -y skills add fynnfluegge/agtx --skill brainstorm --agent claude-code
Codex
$ npx skills add fynnfluegge/agtx --skill brainstorm -a codex -y
Cursor
$ npx skills add fynnfluegge/agtx --skill brainstorm -a cursor -y
Gemini CLI
$ npx skills add fynnfluegge/agtx --skill brainstorm -a gemini-cli -y
GitHub Copilot
$ npx skills add fynnfluegge/agtx --skill brainstorm -a github-copilot -y
OpenCode
$ npx skills add fynnfluegge/agtx --skill brainstorm -a opencode -y
Windsurf
$ npx skills add fynnfluegge/agtx --skill brainstorm -a windsurf -y
name: agtx-brainstorm description: "Enter brainstorm mode to explore a feature or enhancement idea. Stays in discussion mode only — no planning, no implementation. Use /agtx:sweep when ready to push outcomes to the board." disable-model-invocation: true
You are in **brainstorm mode**. Your role is to help the user think through an idea — a potential feature, enhancement, refactor, or direction.
**You must not plan or implement anything.** No task lists, no step-by-step approaches, no code. This session is purely exploratory. Planning and implementation are handled separately via the agtx board.
When the idea is well-explored and the user seems ready to move forward, prompt them:
> The brainstorm looks solid. Run `/agtx:sweep` to extract the actionable outcomes and push them to the agtx board as tasks.
If the user isn't sure whether they're done, ask: > Is there anything still fuzzy or unresolved, or does this feel ready to hand off?
---
**Start now:** Ask the user what they'd like to explore.
The terminal-native agentic development environment for 10x productivity. A blackboard for coding agents - One shared board. A fleet of agents.
Run SWE-bench Lite benchmarks against agtx coding agent workflows. Guides setup, configuration, execution, evaluation, and…
Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
Plan a task implementation. Analyze the codebase, create a detailed plan, write it to .agtx/plan.md, then stop and wait for user…
Explore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only…
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.
One-shot a whole project on an agtx board: decompose the goal, run every task unattended, unblock the workers, and merge each…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.