Kanban Md logo

Kanban Md

Community
antopolskiy
kanban-md

Manage project tasks using kanban-md, a file-based kanban board CLI. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or project metrics.

Overview

Publisherantopolskiy
Repositorykanban-md
Skill namekanban-md
Stars
226
Forks
34
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by antopolskiy on GitHub. Read the source before you install it.

Installation

Install the Kanban Md AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/antopolskiy/kanban-md/tree/main/.agents/skills/kanban-md
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/antopolskiy/kanban-md.git /tmp/kanban-md
mkdir -p .claude/skills
cp -r /tmp/kanban-md/.agents/skills/kanban-md .claude/skills/kanban-md
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kanban Md in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kanban Md on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kanban Md is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

kanban-md

Manage kanban boards stored as Markdown files with YAML frontmatter. Each task is a .md file in kanban/tasks/. The CLI is kanban-md (alias kbmd if installed via Homebrew).

Current Board State

!kanban-md board 2>/dev/null || echo 'No board found — run: kanban-md init --name PROJECT_NAME'

Rules

  • Use --compact for listing commands (list, board, metrics, log) to get token-efficient one-line output.
  • Use kanban-md show ID (default table format) to read task details — it includes the full body and all fields in a human-readable layout. Only add --json when you need to pipe the output to another tool or parse fields programmatically.
  • Always pass --yes when deleting (kanban-md delete ID --yes).
  • Dates use YYYY-MM-DD format.
  • Statuses and priorities are board-specific. Check the board state above or run kanban-md board to discover valid values before using them.
  • Default statuses: backlog, todo, in-progress, review, done, archived.
  • Default priorities: low, medium, high, critical.

Decision Tree

User wants to...Command
See board overview / standupkanban-md board --compact
Get a unique agent name (for claims)kanban-md agent-name
List all taskskanban-md list --compact
List tasks by statuskanban-md list --compact --status todo,in-progress
List tasks by prioritykanban-md list --compact --priority high,critical
List tasks by assigneekanban-md list --compact --assignee alice
List tasks by tagkanban-md list --compact --tag bug
List blocked taskskanban-md list --compact --blocked
List ready-to-start taskskanban-md list --compact --not-blocked --unblocked --status todo
List tasks with resolved depskanban-md list --compact --unblocked
Find a specific taskkanban-md show ID
Claim next available taskkanban-md pick --claim <agent> --status todo --move in-progress
Create a taskkanban-md create "TITLE" --priority P --tags T
Create a task with bodykanban-md create "TITLE" --body "DESC"
Create and immediately claim a taskkanban-md create "TITLE" --priority P --claim <agent>
Start working on a taskkanban-md move ID in-progress --claim <agent>
Advance to next statuskanban-md move ID --next
Move a task backkanban-md move ID --prev
Complete a taskkanban-md move ID done
Edit task fieldskanban-md edit ID --title "NEW" --priority P
Add/remove tagskanban-md edit ID --add-tag T --remove-tag T
Set a due datekanban-md edit ID --due 2026-03-01
Block a taskkanban-md edit ID --block "REASON"
Unblock a taskkanban-md edit ID --unblock
Add a dependencykanban-md edit ID --add-dep DEP_ID
Set a parent taskkanban-md edit ID --parent PARENT_ID
Append a note to task bodykanban-md edit ID --append-body "note" --timestamp
Hand off a task to reviewkanban-md handoff ID --claim <agent> --note "…" --release
Soft-delete with confirmation semanticskanban-md delete ID --yes
Archive a task explicitlykanban-md archive ID
See flow metricskanban-md metrics --compact
See activity logkanban-md log --compact --limit 20
See recent activity for a taskkanban-md log --compact --task ID
Get a board context summarykanban-md context
Initialize a new boardkanban-md init --name "NAME"

Core Commands

list

bash
kanban-md list [--status S] [--priority P] [--assignee A] [--tag T] \
  [--sort FIELD] [-r] [-n LIMIT] [--blocked] [--not-blocked] \
  [--parent ID] [--unblocked] [--unclaimed] [--claimed-by AGENT] \
  [--class C] [--archived] [--group-by FIELD]

Sort fields: id, title, status, priority, created, updated, due. -r reverses. --unblocked shows tasks whose dependencies are all at terminal status.

create

bash
kanban-md create "TITLE" [--status S] [--priority P] [--assignee A] \
  [--tags T1,T2] [--due YYYY-MM-DD] [--estimate E] [--body "TEXT"] \
  [--parent ID] [--depends-on ID1,ID2] [--class C] [--claim AGENT]

Prints the created task ID and summary. --claim immediately claims the task for an agent, combining creation and claiming in one step.

show

bash
kanban-md show ID
kanban-md show ID --archived  # include archived direct children
kanban-md show ID --json   # only when piping to another tool

Default format shows all fields including the body in a readable layout. Use --json only when you need to parse fields programmatically. For the JSON schema, see references/json-schemas.md.

agent-name

bash
kanban-md agent-name

Generates a random two-word identifier (e.g. frost-maple) to use as a claim name. Run once per agent session and remember the result.

edit

bash
kanban-md edit ID[,ID,...] [--title T] [--status S] [--priority P] [--assignee A] \
  [--add-tag T] [--remove-tag T] [--due YYYY-MM-DD] [--clear-due] \
  [--estimate E] [--body "TEXT"] [-a "TEXT"] [--started YYYY-MM-DD] [--clear-started] \
  [--completed YYYY-MM-DD] [--clear-completed] [--parent ID] \
  [--clear-parent] [--add-dep ID] [--remove-dep ID] \
  [--block "REASON"] [--unblock] [--class C] \
  [--claim AGENT] [--release] [-t]

Only specified fields are changed. Prints a confirmation message. -a / --append-body appends text to the existing body without replacing it. -t / --timestamp prefixes a timestamp line when appending. --claim claims (or renews a claim on) the task for the agent. --release releases the claim on the task. Accepts comma-separated IDs for bulk edits.

move

bash
kanban-md move ID[,ID,...] STATUS
kanban-md move ID --next
kanban-md move ID --prev
kanban-md move ID STATUS --claim AGENT

Auto-sets Started on first move from initial status. Auto-sets Completed on move to terminal status. Accepts comma-separated IDs for bulk moves. --claim claims the task during the move (useful when resuming a parked task).

pick

bash
kanban-md pick --claim AGENT [--status S] [--move STATUS] [--tags T1,T2] \
  [--parent ID] [--no-body]

Finds the highest-priority unclaimed, unblocked task and claims it in the same command. Use --status to restrict which column to pick from. Use --move to move the task in that operation. This replaces the slower list → claim → move sequence. Claims are cooperative leases rather than a distributed transaction. By default the result includes full task details; use --no-body when the one-line confirmation is enough.

handoff

bash
kanban-md handoff ID --claim AGENT [--note "TEXT"] [--block "REASON"] [--release] [-t]

Moves the task to review, appends a handoff note, and optionally marks it blocked and/or releases the claim. Use when parking work for another agent or waiting on user input. -t adds a timestamp.

context

bash
kanban-md context [--sections in-progress,blocked,overdue,recently-completed] \
  [--days N] [--write-to FILE]

Generates a markdown board summary suitable for embedding in CLAUDE.md or AGENTS.md. --write-to writes (or updates) the summary inside a delimited block in the target file.

delete

bash
kanban-md delete ID --yes

Moves the task to archived; the task file remains on disk. Always pass --yes because non-interactive contexts cannot answer the confirmation prompt.

archive

bash
kanban-md archive ID[,ID,...] [--claim AGENT]

Moves tasks to archived without a confirmation prompt. Pass the current claim name when archiving an actively claimed task.

board

bash
kanban-md board

Shows board overview: task counts per status, WIP utilization, blocked/overdue counts, priority distribution.

metrics

bash
kanban-md metrics [--since YYYY-MM-DD]

Shows throughput (7d/30d), avg lead/cycle time, flow efficiency, aging items.

log

bash
kanban-md log [--since YYYY-MM-DD] [--limit N] [--action TYPE] \
  [--task ID]

Common action types: create, edit, move, delete, block, unblock, claim, release, handoff, and priority.

Global Flags

All commands accept: --json, --table, --compact (alias --oneline), --dir PATH, --no-color.

Workflows

Daily Standup

  1. kanban-md board --compact — board overview
  2. kanban-md list --compact --status in-progress — in-flight work
  3. kanban-md list --compact --blocked — stuck items
  4. kanban-md metrics --compact — throughput and aging
  5. Summarize: completed, active, blocked, aging items

Triage New Work

  1. kanban-md list --compact --status backlog --sort priority — review backlog
  2. For items to promote: kanban-md move ID todo
  3. For new items: kanban-md create "TITLE" --priority P --tags T
  4. For stale items: kanban-md archive ID

Sprint Planning

  1. kanban-md board --compact — current state
  2. kanban-md list --compact --status backlog,todo --sort priority — candidates
  3. Promote selected: kanban-md move ID todo
  4. Assign: kanban-md edit ID --assignee NAME
  5. Set deadlines: kanban-md edit ID --due YYYY-MM-DD

Complete a Task

  1. kanban-md move ID done — marks complete, sets Completed timestamp
  2. kanban-md show ID --json — verify status and timestamps

Track a Bug

  1. kanban-md create "Fix: DESCRIPTION" --priority high --tags bug
  2. kanban-md edit ID --body "Steps to reproduce: ..."

Track a Dependency Chain

  1. Create parent: kanban-md create "Epic title"
  2. Create subtask: kanban-md create "Subtask" --parent PARENT_ID
  3. Or add dependency: kanban-md create "Task B" --depends-on TASK_A_ID
  4. List tasks ready after dependencies resolve: kanban-md list --compact --unblocked

Agent Cheatsheet

Quick-reference for the agent task lifecycle. These are combination commands — multiple flags in one call to minimize round-trips. Replace <agent> with your session's agent-name output.

Session start

bash
kanban-md agent-name                             # generate a unique claim name; remember it
kanban-md board --compact                        # orient: what's active, blocked, overdue

Claim next task (single-step pick + move)

bash
# Pick highest-priority unclaimed task from todo and move it to in-progress in one step
kanban-md pick --claim <agent> --status todo --move in-progress

# If todo is empty, pick from backlog
kanban-md pick --claim <agent> --status backlog --move in-progress

Pick already prints full task details; add --no-body only when they are unnecessary.

Create and claim in one shot

bash
# Create a task and immediately claim it
kanban-md create "TITLE" --priority high --tags bug --claim <agent>

# Add a body separately (or use --body inline if short)
kanban-md edit <ID> --body "Steps to reproduce: ..."

Progress note (renews claim, appends without overwriting)

bash
# Leave a timestamped note while keeping your claim active
kanban-md edit <ID> -a "Implemented X, running tests." -t --claim <agent>

Finish task (release claim + mark done)

bash
# Run from board home, after merging
kanban-md edit <ID> --release
kanban-md move <ID> done

Park / handoff (moves to review, appends note, releases claim)

bash
# Waiting on user decision or external action
kanban-md handoff <ID> --claim <agent> \
  --note "Ready to merge: branch task/<ID>-…; waiting for: ..." \
  -t --release

# Blocked on something specific
kanban-md handoff <ID> --claim <agent> \
  --block "Reason for block" \
  --note "What's needed to unblock and next step." \
  -t --release

Resume a parked task

bash
kanban-md edit <ID> --claim <agent>                  # re-claim
kanban-md edit <ID> --unblock --claim <agent>        # unblock (if it was blocked)
kanban-md move <ID> in-progress --claim <agent>      # move back to in-progress

Bulk operations (comma-separated IDs)

bash
# Tag multiple tasks at once
kanban-md edit <ID1>,<ID2>,<ID3> --add-tag layer-3

# Move multiple tasks
kanban-md move <ID1>,<ID2> todo

# List with combined filters
kanban-md list --compact --status backlog --priority high,critical --sort priority
kanban-md list --compact --not-blocked --status todo   # tasks ready to start
kanban-md list --compact --status in-progress,review   # all active/parked work

Pitfalls

  • DO use --compact for listing, board, metrics, and log commands — it is the most token-efficient format.
  • DO use kanban-md show ID (default format) to read task details — it is readable and includes the full body.
  • DO pass --yes on delete. Without it, a non-interactive command exits with a confirmation-required error.
  • DO use pick --claim <agent> --status todo --move in-progress rather than list → edit → move — one operation minimizes the coordination window and records ownership immediately.
  • DO use -a / --append-body with --claim <agent> when adding progress notes — this renews the claim and appends without overwriting the body.
  • DO NOT use --json unless you are piping output to another tool or parsing fields programmatically. Default and --compact formats are sufficient for reading.
  • DO NOT hardcode status or priority values. Read them from kanban-md board --compact.
  • DO NOT use --next or --prev without checking current status. They fail at boundary statuses.
  • DO NOT pass both --status and --next/--prev to move. Use one or the other.
  • DO quote task titles with special characters: kanban-md create "Fix: the 'login' bug".
  • DO escape backticks in --body and --append-body values. Shell interprets backticks (`) and $(...) inside double quotes as command substitution, which will execute the text as commands. Escape every backtick with a backslash: \` or use single quotes for the outer string if possible.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Kanban Md AI skill do?

Manage project tasks using kanban-md, a file-based kanban board CLI. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or project metrics.

Why use Kanban Md on TypingMind?

Because you install it once and use it with any model. Kanban Md is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kanban Md in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/antopolskiy/kanban-md/tree/main/.agents/skills/kanban-md. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Kanban Md?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kanban Md?

As many as you like. As long as a model supports skills, you can use Kanban Md with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kanban Md AI skill free?

Yes. It is published on GitHub by antopolskiy under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇