Release: v0.2.0
Highlights
Native system prompt support for Claude and Gemini. Agent definitions are now passed as system-level context instead of being concatenated into user prompts, improving instruction adherence and output quality.
Codex broker execution model. Rewritten Codex reference with a state-machine approach that keeps Codex focused on the sub-agent result instead of starting independent analysis.
Changed
- Claude backend uses
--append-system-promptwith acwd:prefix to separate agent definitions from user prompts - Gemini backend uses
GEMINI_SYSTEM_MDenvironment variable pointing to the agent definition file - Codex and Cursor backends unchanged (concatenated prompt)
load_agent()now returns agent file path as a fourth elementexecute_agent()accepts optionalagent_fileparameter for backends that support file-based system prompts
Fixed
- Operator precedence bug in status determination:
exit_code == 0 or ... and resultnow correctly grouped with parentheses
Improved
references/codex.mdrewritten: purpose-driven structure, abstracted tool names, broker execution model with explicit allowed actions