handoff

Close out the current thread of work on programme $1 (resolve as /programme:resume does).

A handoff whose structure is right and whose content is a changelog is worthless. What makes one valuable is what got noticed during the work. Ask accordingly.

1. Measure the state yourself

Read .claude/session-continuity.json if it exists for docsRoot and compareBranch, as /programme:init does. Never accept a figure from this conversation — including one you stated earlier.

git fetch
git status --short
git log --oneline -10
git rev-list --count "<compareBranch>..HEAD"
git rev-parse HEAD

Run every gate in the ledger's Gates table and record the real output in last run and result. If the Gates table is empty, ask what this project's gates are and fill it, including the trust column and the flake rate for any gate that has one.

2. Interview — do not fill blanks

Draft all five answers before asking anything. Each cites its evidence — a commit sha, a command and its output, a file:line, a gate run. Questions 4 and 5 look forward; for them, evidence means the arc row, or the spec or plan at file:line, that the answer derives from. Then, by the programme's mode — INDEX.md's mode cell, read as INDEX.md's header comment states (the session-start Mode: line reports the same as of session start; if they differ, the cell wins):

• assisted — show the whole draft; the user edits or approves each answer.
• supervised — ask the user only the questions whose draft has no evidence; keep the rest.
• autonomous — keep only the answers with evidence and leave the others out of the ledger entirely — no UNVERIFIED placeholder. The second ask on question 2, below, does not apply.

The questions are not interchangeable with "what did you do?", which produces a changelog.

1. What did you measure? Not what you did — what number, output, or observation do you now have that you did not have before?
2. What did you get wrong, and what would the next session repeat if you do not say so?
3. Which claims already in the ledger are now false?
4. What is the next terminal condition — a command, and the output that means it is done?
5. Does the next phase still sit where ## The arc says — and is any later phase's work cheaper taken now? Ask it against the table, row by row, not from memory. Two shapes to name out loud: work this phase would build that a planned phase later deletes, and work scoped out as "a later phase's" that costs less inside this one than it will on its own. If the answer is "nothing to change", name which rows you read to conclude that — the failure this question exists to catch is answering it from memory.