benchmark
Run SWE-bench Lite benchmarks against agtx coding agent workflows. Guides setup, configuration, execution, evaluation, and reporting.
Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
$ npx -y skills add fynnfluegge/agtx --skill agtx-execute --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/agtx-executeContext preview
The summary Claude sees to decide when to auto-load this skill.
Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
name: agtx-execute description: Execute an approved implementation plan. Implement the changes, then write a summary to .agtx/execute.md and stop.
You are in the **execution phase** of an agtx-managed task.
The argument to this command is a task ID.
If `.agtx/plan.md` exists in the current working directory, read it — it already contains the approved plan and all needed context. Do NOT call `get_task`.
If `.agtx/plan.md` does not exist, fetch the task description:
mcp__agtx__get_task(task_id: "<the id passed to this command>")
1. Read `.agtx/plan.md` if it exists (skip `get_task`), otherwise fetch via `get_task` 2. Implement the changes 3. Run relevant tests to verify your changes 4. Fix any issues found during testing 5. Commit. `git add -A`, commit with a short imperative message, verify `git status --short` clean. Your worktree is deleted at task completion — uncommitted work is destroyed and the merge is blocked. agtx's own files are already git-excluded, so `add -A` takes only your work.
When implementation is complete, write a summary to `.agtx/execute.md` in the **current working directory** with these sections:
What files were modified/created and what was changed in each.
How you verified the changes — tests run, results, manual checks.
After writing `.agtx/execute.md` (in the current working directory):
Terse. No pleasantries. Fragments OK. Short synonyms. Code exact. Status updates: one line. Pattern: [what] [why]. Done.
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 reporting.
Plan a task implementation. Analyze the codebase, create a detailed plan, write it to .agtx/plan.md, then stop and wait for user approval before making any…
Explore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only exploration — do not modify any…
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.
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…
One-shot a whole project on an agtx board: decompose the goal, run every task unattended, unblock the workers, and merge each one. Use when the user wants a…