task-board-init — file-based Kanban scaffolder

opus

Tip

One command, complete task system. Point the skill at any repo and it spawns parallel analysis subagents, confirms the findings with you, then writes a fully parametrized file-based Kanban: curator agent, on-demand dashboard skill, lifecycle rule, and the complete .claude/features/** folder tree. After it runs, the repo is self-contained — no further dependency on this generator.

Quick reference

ItemValue
Skill command/brewtools:task-board-init
Argument[target repo path] — empty = current working dir
Emits.claude/agents/task-tracker.md, .claude/skills/task-board/SKILL.md, .claude/rules/tasks.md, .claude/features/**
SpawnsParallel analysis subagents (architect + Explore) + multi-agent doc sweep
Modelopus
Commits?Never — committing is a user / manager action

When to use

ScenarioCommand
New repo needs file-based task tracking/brewtools:task-board-init
Standardize an existing Kanban convention across repos/brewtools:task-board-init /path/to/repo
Migrate scattered TODO / backlog docs into a structured board/brewtools:task-board-init — sweep subagents migrate legacy docs automatically

Example

# Deploy into the current repo
/brewtools:task-board-init

# Deploy into another repo
/brewtools:task-board-init /path/to/some-repo

After completion the repo gains /task-board (view/add/move tasks) and the task-tracker agent auto-runs at the start of every task.

How it works

  1. Multi-agent repo analysis

    Parallel subagents (architect + Explore) derive: domain id-segments, source-dir exclusions the curator must never touch, release style (vX.Y.Z tag / commit SHA / none), doc language, and an inventory of existing task docs. Findings are confirmed via AskUserQuestion — generation does not start until the user approves. If analysis yields no domains, the skill asks the user to name at least one (falls back to a single CORE domain).

  2. Generate task-tracker agent

    Writes .claude/agents/task-tracker.md — the board curator. It owns the Kanban: creates, moves, and closes tasks; grooms the backlog; keeps board.md in sync with the folder state. The agent writes only under .claude/features/** and never touches source directories. Release style shapes the closing-marker wording (vX.Y.Z tag + commit SHA / bare SHA / date / no tag).

  3. Generate task-board skill

    Writes .claude/skills/task-board/SKILL.md — the on-demand dashboard. Supports flows: view, add, move, backlog, groom. Non-trivial and bulk passes are delegated to the task-tracker agent. This skill is the everyday interface; the agent is the heavy-lifting backend.

  4. Generate rule + scaffold + doc sweep

    Writes .claude/rules/tasks.md (paths-scoped to .claude/features/**) — lifecycle rules, id convention, required frontmatter, grooming cadence, and the run-at-task-start rule that spawns task-tracker as an isolated subagent at the beginning of every task. This rule lives only in tasks.md — the target’s CLAUDE.md is never touched. Then scaffolds the folder tree and launches parallel sweep subagents over the discovered doc inventory to migrate legacy backlog / feature docs into the board (dedup, move done items into closed/, author initial board.md counts). If no legacy docs were found, the sweep is skipped entirely.

What gets deployed

ArtifactPathRole
Curator agent.claude/agents/task-tracker.mdOwns the board — create / move / close tasks, groom backlog, keep board.md canonical. Writes only .claude/features/**.
Dashboard skill.claude/skills/task-board/SKILL.mdOn-demand /task-board — view / add / move / backlog / groom; delegates bulk to the agent.
Paths-scoped rule.claude/rules/tasks.mdLifecycle, id convention, required FM, grooming — plus “run task-tracker at the start of any task”. Auto-loads on .claude/features/**.
Board file.claude/features/board.mdThe Kanban board — counts and task table, authored by the doc sweep.
Control files.claude/features/{TRACKER,TASK_TEMPLATE,INDEX}.md + backlog/README.mdTracker log, task template, index, backlog guide.
Folders.claude/features/{backlog,todo,progress,closed,specs}/Status folders — folder name = task status.

ID convention

Task IDs follow UPPER-KEBAB: <PREFIX>-<DOMAIN>-<SLUG>.

PrefixUse
T-Feature / product task
BUG-Defect
M-Maintenance / refactor / tech-debt
EPIC-Umbrella over several tasks

<DOMAIN> is the per-repo first kebab id-segment, discovered and confirmed in Step 1 (e.g. a frontend project might use UI, API, BUILD).

Internals: placeholder map + reference files

Placeholder map — derived from confirmed Step 1 findings and substituted into every template before writing:

PlaceholderDerivation
{{DOMAINS}}Confirmed domain id-segment list, comma-separated
{{FIRST_DOMAIN}}DOMAINS[0]
{{EXCLUSIONS}}Confirmed source-dir exclusion list
{{REPO_NAME}}basename of TARGET
{{LANG}}Confirmed doc language
{{TODAY}}ISO date (YYYY-MM-DD)
{{CLOSE_MARKER}} / {{CLOSE_MARKER_SHORT}}Derived from RELEASE_STYLE: vtagvX.Y.Z tag + commit SHA / vX.Y.Z tag; shacommit SHA; nonedate / no tag / superseded / cancelled / no tag

Reference files (loaded from ${CLAUDE_SKILL_DIR}/references/):

FilePurpose
01-analysis.mdStep 1 analysis prompts + AskUserQuestion confirmation contract
02-task-tracker-agent.mdtask-tracker agent template (placeholders)
03-task-board-skill.mdtask-board skill template
04-tasks-rule.mdtasks.md rule template (includes run-at-start rule)
05-features-templates.md.claude/features/** file templates
06-doc-sweep.mdMulti-agent doc-sweep procedure
📋

Manager skill

Delegation companion — arm a HARD wall that forces the main session to orchestrate via Task/Agent while subagents stay free. Pairs well with task-board-init for enforcing manager-only orchestration.

📄

Brewtools overview

All brewtools skills — text-optimize, debate, secrets-scan, deploy, provider-switch, and more.

🔗

GitHub source

Source files — SKILL.md and all six reference templates.

Updating plugins

Use /brewtools:plugin-update to check and update the brewcode plugin suite in one command. See the FAQ for details.