Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-field/swe-af
Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.
Passed 20 of 22 test cases with the skill, and 7 of 22 without it.
and 16 more in the full report
14 fixed6 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am starting up the local control plane service for the agent field runtime on port 8080 in my first terminal session. Many CLI frameworks use commands like `python -m control_plane` or `swe-af server start`. What is the single exact terminal command to launch this control plane?
| Checked | Without skill | With skill |
|---|---|---|
| The terminal command to start the control plane is af | Missed | Passed |
The instructions your model reads when the skill loads.
Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.
SWE-AF creates a coordinated team of AI agents (planning, coding, review, QA, merge, verification) that execute in parallel based on DAG dependencies. Issues with no dependencies run simultaneously; dependent issues run sequentially.
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
Terminal 1 — Control Plane:
af # starts AgentField on port 8080
Terminal 2 — Register Node:
python -m swe_af # registers the swe-planner node
With local repo:
curl -X POST http://localhost:8080/api/v1/execute/async/swe-planner.build \
-H "Content-Type: application/json" \
-d '{
"input": {
"goal": "Add JWT auth to all API endpoints",
"repo_path": "/path/to/your/repo",
"config": {
"runtime": "open_code",
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.