Writes a handover document so another person, another agent, or a different tool can pick up multi-session work cold. Use when handing work to someone else, switching tools, or pausing work that will not resume in the same session.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Within one session, the harness handles continuity: context compaction, session resume, and memory files. A handover doc is for the moment that breaks: a different person, a different agent tool, or a fresh session days later. Write it for a reader who has none of your context.
Capture state from the repo, not from memory:
git status (uncommitted changes?)Document completed work — What was done, key decisions (link vibe-decision-journal entries), problems solved and how.
Document remaining work — What's left, what's blocked and on what, known issues introduced, and approaches already tried and rejected (so the next person doesn't retry them).
Write a resume prompt — A self-contained prompt the next session can be started with: branch, files to read first, the next concrete task, and how to verify it.
Order it current-state-first. The top of the doc is what the next reader acts on. Move superseded plans and history to the bottom or to a separate file; a resume file that grows into a history slows every pickup.
Save to docs/handover/YYYY-MM-DD-<topic>.md (or docs/HANDOVER.md for a single rolling doc), and commit it if the next reader will work from a fresh clone.
When a session must stop mid-work, especially with agents running:
CONTINUE.md at the root works well)When the owner says pause ("just note it down"), write the note and plan, then stop. Don't keep building.
Date: [today] · Branch: [branch] · Last commit: [sha] Tests: [pass/fail counts, command used]
[Self-contained prompt: context, branch, files to read first, next step, how to verify.]
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Validates completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.
The English summary is being prepared. Showing the original description.
Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource exhaustion, malformed data, and requirement-linked traceability tests. Use after happy-path tests exist and before claiming coverage is complete, when requirements lack tests, or before a security review.
The English summary is being prepared. Showing the original description.
Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, silently dropping requirements, or claiming work is done without running it. Use before declaring a task complete and whenever a test or requirement feels like it's in the way.
The English summary is being prepared. Showing the original description.
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.
The English summary is being prepared. Showing the original description.
Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing tests that involve goroutines, async operations, or shared mutable state.
The English summary is being prepared. Showing the original description.
Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and spec-to-code implementation mapping. Use before claiming code is complete.
The English summary is being prepared. Showing the original description.