istosandClaude Fable 5 f8d1bf252d Launch headless agents with permissions that allow their own contract (task 05)
Work agents were launched under acceptEdits with no Bash allowlist, so
headless runs could edit files but never run tests or commit — the exact
contradiction card 05 documents. Each launch intent (work, act-pr,
review) now carries a permissions.allow list granting exactly what its
prompt demands, delivered through the same generated settings JSON as
the event hooks. Project test/check commands arrive as neutral prefixes
via BOARD_AGENT_COMMANDS; a new opencode adapter renders the same three
stances in its config language as the portability proof. A clean agent
exit with an empty branch no longer advances the card to review.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-29 19:46:23 +02:00

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.

Install into a repo

git clone <this repo> .task-manager && rm -rf .task-manager/.git
./.task-manager/start.sh        # wires the project (idempotent) and serves

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.

Update

# in manager/local/.env:  BENCH_SOURCE=<this repo's git url>
./.task-manager/update.sh              # latest
BENCH_REF=v1 ./.task-manager/update.sh # a specific release tag

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.

The three-layer law

Core knows about tasks, worktrees, PRs and events. It knows nothing about any particular app (drivers do: local/driver/start), agent vendor (adapters do: core/adapters/), or project (local/ does). Full docs in CLAUDE.md; the adapter contract in manager/core/adapters/README.md.

S
Description
Bench is a local task manager that integrates with coding agents to make it easier to manage work in a repo.
Readme MIT
1.7 MiB
Languages
Python 78.2%
HTML 17.5%
CSS 2.1%
Shell 2%
JavaScript 0.2%