Handoff
Use when a coding session is getting long, before stopping complex implementation/migration/debugging work, when the operator says "prepare a handoff" / "hand this off" / "continue in a new chat" / "/handoff", or when a long autonomous run needs continuity (Mode run-ledger, announced in chat) — archives the superseded restart state to docs/tmp/handoff/archive/ (paper trail), then writes the active state to docs/tmp/handoff.md so a fresh AI session resumes from the exact current point without the previous chat. Do NOT use for routine commits, human-facing status reports, formal implement/deploy role relays (those are docs/tmp/handoff/<date>-<slug>-{implement,deploy}.md), or when no meaningful code/test/schema/config/decision change happened this session.From its SKILL.md
npx -y skills add fusebase-dev/fusebase-flow --skill handoffAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
11.2 KB, as published. Nobody here has run it
Handoff
Style: Mode-B-lite. Produces the active-continuity artifact
docs/tmp/handoff.md(FR-23 Tier 2) for the NEXT AI coding agent — not a human PM report. Operator-triggered (invocation: manual) for restart mode;Mode: run-ledgeris the sole sanctioned autonomous write (long-run continuity, announced in chat).
Purpose
Capture the exact current state of a coding session into docs/tmp/handoff.md so a brand-new AI session continues without the previous chat. Long sessions degrade and compaction is lossy; a structured handoff preserves goal, repo state, decisions, in-flight files, failed attempts, constraints, and the single next action. This is the active restart state; formal role-relay prompts (implement/deploy/architect) are separate dated files under docs/tmp/handoff/ produced by implementation-planning / release-deploy-reporting.
Two modes (header Mode: line; absent in a legacy file → treat as restart): restart — operator-triggered snapshot for the next session; run-ledger — a long autonomous run's continuity note, written without operator trigger and announced in chat (one line), so context death mid-run loses nothing. A fresh session reading Mode: run-ledger resumes from records (read the ledger + cited artifacts first, resume from the last durable fact — task-delegation successor contract); a run-ledger is a continuity note, not a role-relay draft (it does not breach "AI Developer acknowledges; doesn't draft").
When to invoke
- Operator says "prepare a handoff" / "hand this off" / "continue in a new chat" / runs
/handoff(→Mode: restart). - Session is getting long / context degrading, or about to stop a complex implementation, migration, or debugging session.
- Meaningful code/test/schema/config/decision changes were made and must survive into the next session.
- A long autonomous run needs continuity across possible context death (→
Mode: run-ledger, no operator trigger needed; announce the write in chat — one line).
Do not invoke when
- No meaningful change happened this session (nothing to continue from) — say so; do not write a hollow file.
- Operator wants a human-facing status update / standup / PR description — this file is for an AI agent.
- The artifact needed is a formal role relay (
docs/tmp/handoff/<date>-<slug>-{implement,deploy}.md) — that'simplementation-planning/release-deploy-reporting. - Operator wants release/deploy reporting — use
release-deploy-reporting.
Required inputs
| Input | Where it lives | If missing |
|---|---|---|
| Repo state | git status --short, git branch --show-current, git rev-parse --short HEAD, git diff --stat | Stop; confirm the working dir is the intended repo |
| Output structure | templates/handoff.md (the 16 canonical sections) | Use that template's section order; do not improvise |
| Session facts | the current conversation (goal, role, decisions, failures, next step) | Write Unknown; never guess |
| Build/test commands | package.json, Makefile, pyproject.toml, repo docs | Detect before inventing; else Unknown |
Procedure
- Classify per FR-23 (
documentation-budget): a handoff is Tier 2 — warranted only when the next session needs exact continuation state. If nothing meaningful changed, stop. - Inspect repo state: branch, short HEAD,
git status --short,git diff --stat; review small diffs. - Detect real build/test/lint commands from manifests. Do not invent.
- Reconstruct session facts: role + authority, goal + non-goals, done/partial/not-started, locked decisions, constraints, what failed and why, open questions, the single next concrete action.
- Mode + archive (paper trail). Stamp
Mode: restart(operator-triggered) orMode: run-ledger(autonomous continuity — announce the write in chat, one line). Archive the predecessor todocs/tmp/handoff/archive/<YYYY-MM-DD-HHMM>-handoff.md(timestamp from itsUpdated:header when parseable, else file mtime/now) ONLY on restart supersede or mode transition (restart↔run-ledger,/handoffover a live ledger, or a different ticket's file). Run-ledger updates supersede IN PLACE (FR-18; git history is the audit trail) — never one archive file per ledger update. Archive files are dated history — agents never load them; the operator may prune the archive anytime (nothing references it). - Create
docs/tmp/if absent. Producedocs/tmp/handoff.mdagainsttemplates/handoff.md— same section order, every section filled with content /Unknown/None, and currentUpdated: <YYYY-MM-DD HH:MMZ>+Mode:lines in the header. Do NOT append resumption notes above old content (FR-18); the superseded restart predecessor lives in the archive. Write primitive (FR-18): supersede replaces stale semantics, not the file. A run-ledger update where most sections are unchanged is a targetedEditof the stale regions + theUpdated:/HEAD:header — not a regeneration. A fullWriteis for a restart snapshot, a mode transition, a different ticket, or when most sections changed. "Fresh" means no stale semantics survive, never retype the file. - Quality bar: factual only; pointers to canonical spec/decisions/tasks instead of reprinting them (FR-23); exactly one concrete executable Next Step; preserve repo terminology; product/user decisions separate from implementation detail; before reusing any copied procedural block, check whether a capability shipped since it was written supersedes the procedure.
- Report a short Mode A summary in chat (Goal, Current state, Active files, Next step, Validation). Do not paste the full file unless asked.
Resuming from a handoff (reader contract)
Named reader: the NEXT session, via workflows/session-initiation.md steps 5/5a (which reads docs/tmp/handoff.md automatically at session start).
- Read the header:
Mode:,Updated:,Branch:,HEAD:. - Trust gate. Diff recorded
Branch:/HEAD:vs livegit branch --show-current/git rev-parse --short HEAD. Match →Active Files in FlightandNext Stepare current; resume there. Mismatch → the repo moved after the write: re-derive in-flight state fromgit status --short+git log <recorded-HEAD>..HEAD --oneline; treat the file table as historical;Key Decisions Made/Failed Attemptsstay valid (they don't decay with HEAD). Mode: run-ledger→ resume from records: read the ledger's cited artifacts BEFORE acting; resume from the last durable fact (task-delegationsuccessor contract).- Never append a resumption note to the file (FR-18) — the next write supersedes in place (targeted
Editwhen most sections are unchanged; fullWriteon a structure/mode/ticket change).
Run-ledger write cadence
Supersede the ledger at durable milestones, not per tool call: after each commit, gate verdict, locked decision, completed T-task/slice, or concluded failed attempt — and BEFORE any operation that could kill context (deploy, migration, long bounded run). Each write = one-line chat announcement. Between milestones the ledger may lag; git history covers the gap. One archive file per update is a violation (in-place supersede — see Procedure step 5).
Output artifacts
| Artifact | Path | Mode |
|---|---|---|
| Active session handoff | docs/tmp/handoff.md | Mode B (16 sections from templates/handoff.md, Updated: + Mode: header) |
| Archived predecessor | docs/tmp/handoff/archive/<YYYY-MM-DD-HHMM>-handoff.md | dated history — never loaded (restart supersede / mode transition only) |
| Handoff summary | chat | Mode A |
Failure cases
| Failure mode | Detection | Response |
|---|---|---|
| Nothing meaningful to hand off | git status clean, no in-flight decisions | Tell operator no handoff is warranted; do not write a hollow file |
| Facts unknown | A section can't be filled from session/repo | Write Unknown; never invent results/decisions |
| Vague next step | Next Step reads "continue" / "fix issues" | Rewrite as one named file/function/command + expected result |
| Stale existing handoff | docs/tmp/handoff.md describes a different/old task | Archive it, then supersede with current state — a different ticket is a full Write (FR-18 write primitive); do not merge contradictory histories |
| Regenerated an unchanged file to "supersede" it | whole-file Write whose diff touches a few regions | Use a targeted Edit; FR-18 replaces stale semantics, not the file |
| Reprinting canonical docs | Handoff restates the full spec/decisions/tasks | Replace with pointers (FR-23) + current state |
Escalation path
- Repo state ambiguous (detached HEAD, mid-rebase, dirty submodules) → record under
Environment / Branch / Repo Stateand ask the operator to confirm before the next session continues. - Session made deploy/production-affecting changes → also route through
release-deploy-reporting; the active handoff is not a deploy record. - Decisions still unsettled → list under
Known Issues / Open Questions, notKey Decisions Made.
Anti-patterns
- Do not write a human-PM / marketing-style document — the reader is an AI agent.
- Do not guess; write
Unknown. - Do not hide failed attempts or dead-end debugging paths.
- Do not emit a vague Next Step.
- Do not include chain-of-thought or unrelated chat history.
- Do not use
docs/tmp/handoff.mdfor a formal implement/deploy relay (those are dated files underdocs/tmp/handoff/). - Do not auto-invoke restart mode (
invocation: manual) — the operator triggers it.Mode: run-ledgeris the sole sanctioned autonomous write and MUST be announced in chat when written. - Do not archive on every run-ledger update (in-place supersede; archive fires on restart supersede / mode transition only).
Clean-room note
Original Fusebase Flow content. The session-continuity-doc concept is common to long-running agent workflows; no third-party code, prompts, or skill files are copied. See docs/source-map.md.