istosandClaude Opus 5
b690060be2
Merge & clean up on a phase card now ends the phase: after the merge into main has actually succeeded, every member the phase merged moves to done/ and its workspace is cleared the way completing an ordinary card clears its own — worktree removed, local branch deleted, branch on the remote deleted. Only what the phase merged. A member is swept when its card settled into review/ or done/ and its branch is contained in the phase branch (or there was never a branch to bring) — the same pair the runner reads a member as merged by. One that halted, was held or was walked back keeps its card, its worktree and its branch: there is work in them. Nothing uncommitted is thrown away: a member's worktree comes out without --force, and a dirty one is reported in the ticker and kept with its branch rather than forced. One ending, told once. taskfiles.move_together moves the cards in a single commit naming all of them (`board: 47, 52 → done with phase 53`, so it publishes in team mode like any other board commit), and the moves are marked quiet so the watcher does not also scroll five identical move lines behind the one line the ending gets. The other endings are untouched: "just move the card" and archiving the phase card move no member, because neither puts anything in main. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Bench
A live kanban for coding-agent work: task files in stage directories are
the only source of truth; a stdlib-only board narrates everything that
happens to them — agents working in git worktrees, PRs opening on review,
CI and Copilot state on the cards, drives of the app from a task's own
branch, and an archive that is never a delete. Turn on team mode
(BOARD_SYNC=1) and the truth is origin/main: moves commit and push
themselves, every board pulls on a beat, and the person who claimed a
card first keeps it.
Docs: bench.12vectors.com — guides, concepts, and a settings reference, every page of it generated from this repository's own markdown, so what the docs say and what bench does cannot drift apart.
bench's own board, running on this repository. Three agents at work, each on its own branch — and every one of them stops at review.
Install into a repo
mkdir .task-manager && curl -L \
https://github.com/12vectors/bench/releases/latest/download/bench.tar.gz \
| tar -xz -C .task-manager
./.task-manager/start.sh # wires the project (idempotent) and serves
No token, no clone: releases are curated artifacts that never contained bench's own cards or settings, so the board starts empty by construction.
The first run asks the two questions it cannot answer for you — solo or
team, and which agent adapter — and writes manager/local/.env from the
documented example, so every other setting is discoverable in your own
copy. What runs your tests is read off the project rather than asked
(package.json → npm test, and so on); nothing recognisable leaves
BOARD_AGENT_COMMANDS empty, and that is the key to set before an agent
can run them. Bare Enter takes the default
throughout; with no terminal (CI, a script) it asks nothing and
install.py --setup asks later.
Commit .task-manager/ into the host repo — core is vendored on purpose,
so clones work offline and updates show up in the host's own diffs.
The workflow brief ships as .task-manager/AGENTS.md — the cross-vendor
name coding agents read natively — with CLAUDE.md beside it as a one-line
compatibility pointer. Both live inside .task-manager/, so a host repo's
own root AGENTS.md is never touched.
Update
./.task-manager/update.sh # latest release
BENCH_REF=v2 ./.task-manager/update.sh # an exact release tag
The artifact is stamped with the repo it was built from, so updating
needs no configuration; BENCH_SOURCE=<owner/repo> in
manager/local/.env overrides the stamp. Updates replace
manager/core/ and the top-level scripts wholesale and touch nothing
else — tasks, plans, reference, and everything under manager/local/
(your driver, commands, prompt overrides, settings, state) survive every
update. Then python3 .task-manager/install.py and restart the board.
If the source repo has no published release yet, update.sh says so and
changes nothing.
Working on bench itself
git clone git@github.com:12vectors/bench.git && cd bench && ./start.sh
A clone carries bench's own cards and local/ content — that is dev mode,
not an install. (Installing from a clone anyway works: install.py
clears the shipped cards on its first boot in a host repo.) Releases are
built by ./release.sh from the manifest at
manager/core/release-manifest: tag = v<VERSION>, one stable asset
name (bench.tar.gz), contents at the tarball root — the two things the
install one-liner above depends on.
The three-layer law
Core knows about tasks, worktrees, PRs and events. It knows nothing about
any particular app (drivers do: manager/local/driver/start), agent
vendor (adapters do: manager/core/adapters/), or project
(manager/local/ does).
The consequence is what makes an update safe: update.sh replaces
manager/core/ wholesale, and everything a project taught bench about
itself lives outside it. Full docs in AGENTS.md — the file
the docs site is cut from, and the one an agent working in your repo
reads; the adapter contract in
manager/core/adapters/README.md.
License
MIT.