istosandClaude Opus 5
a3388ed2ea
Card 56 took a phase's members off the Board; this is where they went. A fourth view beside Board, Sessions and Focus, holding one lane per phase card — every phase there is, not only the running ones, because a phase whose cards are all merged and which is waiting on its own PR still owns them. A lane is a head, five stage columns and the phase's log. The head carries the phase, its progress, the member in flight and its own controls — hold, the phase branch, the phase card — and nothing that ends a phase, which stays a board move on the phase card. Four columns are the board's stages; the fifth is 'Merged in', not done/, because a member merged into the phase branch is finished as far as the phase is concerned and is not in main yet. Which members the branch holds is the runner's last pass while a phase runs, and the phase log once there are no more passes, so a phase in review/ still draws the work where it landed. The cards are the cards: cardFor() builds them here exactly as it builds them for the Board, agent line, chips, position-in-the-run chip and hover actions intact. The phase log sits under the lane, the runner's decisions in the order it made them, read off the card's own '## Phase log' — the only thing that can tell "not reached yet" from "started and ended badly". A halted lane says so at the top of itself, names the card it stopped on, and offers run again beneath the reason. That action left the Board's phase card for the same reason: clearing a halt should mean having read what caused it, so the card offers a way into the view instead, and hold, which needs nothing read. The crossing the other way is the switcher, which carries how many phases are running and an alarm mark while one has halted — on every view, alongside the toast and the ticker line that already fire. Covered by tests/test_phases_view.py: collect() reads a throwaway tasks/ tree and the page's own lane rules run over that reading in node (ordering, placement, the last column, the log, the all-merged phase in review/), plus source-level wiring invariants for the DOM half. test_phase_watch, test_card_actions and test_scroll_kept updated where this moves what they pin. Full suite green: 939 tests. 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.