full loop
End to end
Requirements go through intake, decisions, build, verification, review, safe fixups, and local commit when gates pass.
[$DeepDone Orchestrate] Build this end to end
Requirements to shipped code: automated.
An automated control system for AI-assisted software work. Works best with Codex.
Implement end to endChoose depth
full loop
Requirements go through intake, decisions, build, verification, review, safe fixups, and local commit when gates pass.
[$DeepDone Orchestrate] Build this end to endbounded
One controlled transition only. Useful when you want intake, one milestone, verification, review, or a commit candidate.
[$DeepDone Orchestrate] Continue one stepWorkflow
Shape work into a small task, one epic, or roadmap. Resume stale state before coding.
Execute one clear milestone. Scope stays narrow. Ledger tracks changed truth.
Run smallest useful checks first. Review local diff for bugs, regressions, security, and missing tests.
Create focused local commits, draft PR or MR material, inspect CI when asked, archive after merge or release.
Most used
deepdone-orchestrateRoutes the whole workflow, enforces mode budgets, and stops on unsafe ambiguity.
deepdone-decideRecords one evidence-backed technical decision before implementation.
deepdone-implementExecutes exactly one milestone and keeps ledger facts current.
deepdone-verifyRuns the smallest convincing checks and logs exact outcomes.
deepdone-reviewReviews local diff for correctness, regressions, security, overscope, and missing tests.
deepdone-commitPrepares or creates a focused local commit after ledger, verification, and review gates pass.
deepdone-prDrafts platform-neutral PR or MR text and inspects CI only when asked.
Skill rack
deepdone-orchestrateDefault entry point for both end-to-end work and single-step control.
Next transition, completed run, local commit, or exact stop reason.
Use $deepdone-orchestrate. Mode: end-to-end.deepdone-planRequirements are new, fuzzy, or large enough to need memory.
Small task, single epic ledger, or roadmap plus active ledger.
Use $deepdone-plan.deepdone-syncThread resumed, diff exists, or next action may be stale.
True state, drift notes, corrected next action.
Use $deepdone-sync.deepdone-advanceCurrent epic is complete and queued work remains.
Updated roadmap and exactly one new active ledger.
Use $deepdone-advance.deepdone-decideArchitecture, library, API, deployment, or schema choice could be wrong from memory.
Decision block with chosen option, rejected options, sources, and verification impact.
Use $deepdone-decide.deepdone-implementNext milestone is clear, acceptance is known, and touched files are obvious.
Focused code change, progress update, next verification path.
Use $deepdone-implement.deepdone-verifyCode changed or a milestone claims done.
Pass, fail, or blocked verification log plus residual risk.
Use $deepdone-verify.deepdone-reviewImplementation and verification are complete enough to challenge.
Findings by severity or review-result pass marker.
Use $deepdone-review.deepdone-fixupReview found clear low-risk defects inside current milestone.
Focused fix, verification result, remaining blocker if any.
Use $deepdone-fixup.deepdone-commitWork is ready to become one VCS unit.
Commit candidate or local commit when authorized.
Use $deepdone-commit.deepdone-prA local commit exists and work needs external review handoff.
Title, body, blockers, or CI summary. No push by default.
Use $deepdone-pr.deepdone-archiveWork is merged or released and you explicitly want closeout.
Archived ledger, roadmap pointer update, post-merge truth.
Use $deepdone-archive.Install and run
The skills repo contains agent manifests, examples, doctor checks, and workflow docs. Clone it once, then start with the orchestrator.
One active thread of work beats parallel plan sprawl.
Every gate records truth where the next run can find it.
Push, merge, deploy, and archive stay explicit.
SKILLS_REPO="https://github.com/lakesoftai/deepdone-agent-skills"
git clone "$SKILLS_REPO" ~/.agents/skills/deepdoneUse $deepdone-orchestrate.
Requirements: <goal>
Mode: end-to-end.Mode: one-step
Mode: until-review
Mode: until-commit-candidate