task.
task carries one unit of work from “understand the request” through to “merged, issue closed, archived.” The engine applies the right DAIC mode on each step and runs the git/issue plumbing automatically — your job is to discuss, write code, and provide verification evidence. Everything else is enforced structurally.
Steps
- 01Investigationread-only
Read-only. Understand scope, align on an approach, compose the task file. No code is written here. This is also the re-planning anchor — any later step returns here when an assumption breaks.
OpusAntigravityCodexyour call — answer to go on - 02Implementationedit tools unlocked
Full edit access. Write code to satisfy every success criterion — no new scope, no drive-by refactors. Stop-on-blocker rather than guess. Changes are not committed yet.
- 03Code-reviewspec gate
The two-stage gate. Stage 1: spec-compliance against the success criteria. Stage 2: parallel code-quality review (Claude + any AI providers). Cannot advance without passing both.
OpusAntigravityCodex - 04Documentationdocs only
Docs-only edits — source edits are hook-blocked. Update affected CLAUDE.md files, finalize the work log, refresh the wiki if enabled.
writes back to the shared LLM wiki - 05Completionsquash & push
You verify, then the engine does all git/issue/archive work automatically: branch merge, push, MR/PR, issue close, archive.
What makes it distinctive
The two-stage code-review gate
Stage 1 (“does the diff match the promise?”) catches well-written code that drifted from spec — the spec-compliance-reviewer audits the diff against your Success Criteria and writes a SPEC_REVIEW: PASSED sentinel. Stage 2 (“is the diff correct/secure?”) dispatches the Claude code-review agent plus one Task per configured AI provider, in parallel. Both stages are post_funcs with stop-on-failure — un-bypassable by construction.
Commits happen only at completion
The LLM never commits prematurely. The engine creates the branch up front (an investigation post-func), but every commit, merge, push and MR/PR lives in the completion step’s engine-driven funcs, which branch on your issue-tracking provider (or present a 4-option menu when none is configured).
Evidence-gated advance
The advance summary out of code-review must carry literal verification evidence — a fenced output block, “N/N passed”, “exit 0” — or the escape hatch no-verification-applicable: <reason>. Prose like “looks good” is rejected.
branch feature/ · fix/ — set by task prefix