gpt-engineer-spark
Lead end-to-end engineering work with a capable main agent and a parallel fleet of model-pinned GPT-5.3-Codex-Spark subagents. Use when the user asks for a Spark fleet, ultra-fast parallel coding agents, rapid repository exploration, many bounded implementation shards, or low-latency independent verification while retaining architecture, integration, and final acceptance with the main agent.
- Version
- 1.4.0
- License
- MIT
Pinned to revision 3f294aed5860, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/gpt-engineer-spark/SKILL.md
- skills/gpt-engineer-spark/agents/openai.yaml
- skills/gpt-engineer-spark/assets/codex/agents/spark-explorer.toml
- skills/gpt-engineer-spark/assets/codex/agents/spark-verifier.toml
- skills/gpt-engineer-spark/assets/codex/agents/spark-worker.toml
- skills/gpt-engineer-spark/assets/read-only-fleet.example.json
- skills/gpt-engineer-spark/references/codex-spark.md
- skills/gpt-engineer-spark/scripts/bootstrap.py
- skills/gpt-engineer-spark/scripts/run_spark_agent.py
- skills/gpt-engineer-spark/scripts/run_spark_fleet.py
- skills/gpt-engineer-spark/scripts/test_bootstrap.py
- skills/gpt-engineer-spark/scripts/test_run_spark_agent.py
- skills/gpt-engineer-spark/scripts/test_run_spark_fleet.py
Every link opens the file at its source, pinned to the revision this page describes.