Agent skill

Wrongstack Kanban

by WrongStack in WrongStack/WrongStack

Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it.

MITAuto-check passedProductivity & Automation

Install Wrongstack Kanban

skills CLI
$ npx skills add WrongStack/WrongStack --skill wrongstack-kanban -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install WrongStack/WrongStack wrongstack-kanban --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/wrongstack-kanban .claude/skills/wrongstack-kanban && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
wrongstack-kanban
GitHub stars
368
Token cost
~2.2k tokens
SKILL.md length
1,182 words
Files
2
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it.

  • Works in 5 steps: Never claim a task is done in chat… → Never mark a task completed without… → Never skip lifecycle stages. Managed… → …
  • Tasks that involve Task management
  • SKILL.md covers What the board is for, Proportional hierarchy, Card detail and Anti-fake-progress rules, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wrongstack Kanban is an agent skill from WrongStack/WrongStack. Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it. Covers card detail, the managed Backlog→Todo→Running→Review→Done lifecycle, lease-fenced dispatch, and what "verified" means before a card reaches Done.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Productivity & Automation, covering Task management and Sprint planning and agile. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

  • Tasks that involve Task management
  • Tasks that involve Sprint planning and agile

Example prompts

  • “verified”
  • “/wrongstack-kanban”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Never claim a task is done in chat without a board mutation. If you
  2. Never mark a task completed without verification. On a managed board
  3. Never skip lifecycle stages. Managed cards move exactly one stage at a
  4. Never report work as in progress without a board assignment. If work is
  5. Never shrink tracked scope by omission. Todo, task and plan rows are

What it can do on your machine

Read from SKILL.md and the folder at commit ec76a20. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wrongstack Kanban loads about 2.2k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 1,182 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from WrongStack/WrongStack at commit ec76a20, republished under its MIT licence (© WrongStack). 1,182 words, ~2,217 tokens.

Download SKILL.mdSave it as .claude/skills/wrongstack-kanban/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
wrongstack-kanban
description
Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it. Covers card detail, the managed Backlog→Todo→Running→Review→Done lifecycle, lease-fenced dispatch, and what "verified" means before a card reaches Done.
trigger
working with the kanban tool, managing project work through boards, or advancing a managed card's lifecycle
version
1.0.0
required-capabilities
work.plan
required-tools
kanban

WrongStack Kanban

What the board is for

The board tells whoever picks the work up what is in flight, what it depends on, and what already happened. It is a record, not a checkpoint. Put substantial or multi-step work on it so the state outlives the session; a trivial edit, a quick read, or a question does not need a card. Resume the existing card for the same request instead of creating a duplicate.

The board follows the work; the work does not wait on the board. If Kanban persistence fails, say so and keep working — do not stall.

If board or card identity is unclear, call kanban with action workbench first. Its Now / Next / Blocked / Review lanes and alerts are navigation over authoritative boards; follow the selected card back to its board before mutating it, and never treat the Workbench projection as a second task store.

Proportional hierarchy

  • A genuinely atomic request is one childless leaf card. It does not need invented children.
  • Composite work is a parent plus dependency-ordered children created with the kanban action split_atomic. Only a parent marked atomic: true needs childTaskIds.
  • Scale card count to the size of the work. Never let card bookkeeping become the task.

Card detail

What a managed board actually enforces before a card leaves Backlog:

FieldRequiredWhy
descriptionYesA title alone is not actionable scope
assignee (or assignedAgent / assignment identity)YesWork without an owner is untracked
successCriteriaYesAcceptance criteria define "done" before work starts
childTaskIdsOnly when atomic: trueA composite parent must name its children; a leaf stays childless

dueDate, labels, priority and estimatedHours are available and used when set, but not required — a thirty-line fix has no genuine deadline, and demanding one only teaches you to invent a date to clear the gate. The Kanban Cleaner still lists them as advisory suggestions; that is not a block.

Fill what is genuinely known. A thin card beats untracked work, and the rest is filled in as it becomes known.

Anti-fake-progress rules

  1. Never claim a task is done in chat without a board mutation. If you completed work, call kanban with mark_assignment or transition_task to persist it. A chat-only completion claim is fake progress.
  2. Never mark a task completed without verification. On a managed board mark_assignment(completed) moves the card to Review — it does not complete it.
  3. Never skip lifecycle stages. Managed cards move exactly one stage at a time. The guard rejects jumps.
  4. Never report work as in progress without a board assignment. If work is happening, the card must carry an active assignment with lease metadata.
  5. Never shrink tracked scope by omission. Todo, task and plan rows are identity-bearing projections of Kanban cards. Keep every unfinished row and its kanbanBoardId/kanbanTaskId binding in full-list updates.

Dispatch contract

  1. Dispatch is deterministic. Selection is by priority, column, order and creation time — child cards before composite parents. Do not try to influence it by shuffling tasks or boards.
  2. Claim before working. Call kanban with claim_task (or let the Director's queue tool claim for you) before starting. Working an unclaimed card means another agent may be working it too.
  3. Heartbeat or lose the lease. Call kanban with heartbeat_assignment before the lease expires. Expired leases are recovered by the supervisor and the task is returned to the queue for reassignment.
  4. Fence your writes. Pass expectedLeaseId on every mark_assignment and heartbeat_assignment. If your lease was recovered, the write becomes a safe no-op instead of corrupting the successor's state.

Completion contract

  1. "Done" means verified. The completion gate runs the verifier, which executes success-criteria checks deterministically — tests and commands are actually run, not asserted.
  2. Chat evidence is not board evidence. Saying "tests pass" verifies nothing. The verifier runs the real command and records the result.
  3. File scope is checked. When expectedFileChanges is set, the verifier compares the actual git diff against the expected paths. Unexpected changes fail the scope check.
  4. Acceptance depends on board policy. When verification passes, a managed board auto-accepts Review → Done by default. A board that sets lifecycle.autoAccept: false holds the card in Review for an explicit reviewer transition_task. Either way, a failing or absent verdict never reaches Done on its own.
Show full SKILL.md (478 more words)Show less

Every material action produces a board mutation

ActionRequired mutation
Start workmark_assignment(running) — a managed card advances to Running with it
Complete workmark_assignment(completed) — a managed card advances to Review
Fail workmark_assignment(failed) with error
Split scopesplit_task or split_atomic
Add evidenceadd_note or add_link
Change planupdate_task or add_dependency
Tick a criterionupdate_check with checkStatus: "passed" (read ids from get_task)

Prohibited patterns

Anti-patternWhy
Creating title-only cards on a managed boardRejected at creation; no description means no actionable scope
Reporting done without board evidenceFake progress; the board is the shared record
Randomizing task selectionDispatch is deterministic by design
Working without a leaseUntracked, and may collide with another agent
Omitting unfinished Todo/task/plan rowsRequirement identity and coverage would be lost
Inventing subtasks for a leaf cardRecursive decomposition to satisfy process, not the work

Out of scope

  • Don't create a card for trivial work. A quick read, a one-line fix, or a question does not need a card. Resume the existing card for the same request instead of creating a duplicate.
  • Don't claim a task is done in chat without a board mutation. Chat-only completion is fake progress. Persist via kanban actions; the board is the shared record.
  • Don't skip lifecycle stages on a managed board. Managed cards move exactly one stage at a time. The guard rejects jumps; trying to bypass it is a bug.
  • Don't work an unclaimed card. Another agent may be working it. Take claim_task first (via kanban), or let the Director's queue claim for you.
  • Don't lose the lease. Heartbeat before the lease expires. An expired lease is recovered by the supervisor and the card returns to the queue.
  • Don't fence-less write. Pass expectedLeaseId on every mark_assignment and heartbeat_assignment. If your lease was recovered, an unfenced write corrupts the successor's state.
  • Don't invent children for a leaf card. Atomic work is one childless leaf. Recursive decomposition to satisfy process is process for process's sake.
  • Don't try to influence dispatch order. Selection is deterministic by priority, column, order, and creation time. Shuffling tasks or boards doesn't change it.
  • Don't block on Kanban persistence. If a board write fails, say so and keep working. The board follows the work; the work does not wait on the board.

Before returning

  • Substantial work has a card with description, assignee, and successCriteria set
  • Card claimed via claim_task (or Director queue) before any work started
  • Lease heartbeated within the lease window
  • Every material action produced a board mutation (no chat-only claims of progress)
  • mark_assignment and heartbeat_assignment carried expectedLeaseId
  • Completion went through the verifier; "Done" means the verifier actually ran
  • Todo/task/plan rows preserve kanbanBoardId / kanbanTaskId bindings in full-list updates
  • Card count scaled to the size of the work; no invented subtasks
  • sdd — spec-driven development creates boards from task graphs
  • bug-hunter — findings can be tracked as cards
  • multi-agent — parallel dispatch through the Director's queue tool

© WrongStack, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in packages/core/skills/wrongstack-kanban of WrongStack/WrongStack.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit ec76a20

Compare with similar skills

Wrongstack Kanban next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Wrongstack Kanban compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wrongstack Kanban this skillWrongStack/WrongStack368—~2.2kAutomated safety check: PassMIT
Kanbaniii-hq/workers113—~1.3kAutomated safety check: PassApache-2.0
Kanban Heartbeatcyanluna-git/cyanluna.skills183—~2.7kAutomated safety check: PassMIT
Frappe Impl UI ComponentsImpertio-Studio/Frappe_Claude_Skill_Package187—~4.2kAutomated safety check: PassMIT
Worklog Synccyanluna-git/cyanluna.skills183—~3.2kAutomated safety check: PassMIT
Kanban Mdantopolskiy/kanban-md223—~4kAutomated safety check: PassMIT

Similar skills

  • Kanban

    iii-hq/workers

    File-backed kanban board: create, read, move and comment on tickets by key or uuid, assign agent profiles, and wake on comments through the kanban:comment trigger instead of polling.

    113 GitHub stars~1.3k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Kanban Heartbeat

    cyanluna-git/cyanluna.skills

    Scan kanban boards for stagnant tasks and optionally mark them.

    183 GitHub stars~2.7k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed
  • Frappe Impl UI Components

    Impertio-Studio/Frappe_Claude_Skill_Package

    A skill your agent uses when building custom dialogs, extending List View, creating Page controllers, or adding Kanban/Calendar views and realtime updates.

    187 GitHub stars~4.2k tokensUpdated 20 days ago
    Productivity & AutomationAuto-check passed
  • Worklog Sync

    cyanluna-git/cyanluna.skills

    Sync kanban board tasks to EOB weekly worklogs. An agent skill from cyanluna-git/cyanluna.skills.

    183 GitHub stars~3.2k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed
  • Kanban Md

    antopolskiy/kanban-md

    Manage project tasks using kanban-md, a file-based kanban board CLI.

    223 GitHub stars~4k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Herdr Board

    nelsonPires5/herdr-board

    Interact with the herdr-board kanban from inside an agent run or an interactive session.

    170 GitHub stars~4.6k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from WrongStack/WrongStack

All 38 skills in this repo
  • Design Craft

    WrongStack/WrongStack

    Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

    368 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Design Critique

    WrongStack/WrongStack

    A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…

    368 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Mailbox Bridge

    WrongStack/WrongStack

    A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…

    368 GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Multi Agent

    WrongStack/WrongStack

    A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.

    368 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Web Platform Baseline

    WrongStack/WrongStack

    Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale…

    368 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Wrongstack Mailbox

    WrongStack/WrongStack

    A skill your agent uses when the user wants to communicate with WrongStack's shared project mailbox from outside WrongStack — read messages sent by WrongStack agents, send replies, broadcast to all…

    368 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

Questions about Wrongstack Kanban

What does Wrongstack Kanban do?

Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it. Wrongstack Kanban is an agent skill from WrongStack/WrongStack. Record substantial project work on WrongStack's IPC-backed Kanban board so it survives the session and other agents can see it.

When should I use Wrongstack Kanban?

Wrongstack Kanban fits situations like: tasks that involve Task management; tasks that involve Sprint planning and agile.

How do I install Wrongstack Kanban in Claude Code?

Run `npx skills add WrongStack/WrongStack --skill wrongstack-kanban -a claude-code`. Or copy the skill folder (packages/core/skills/wrongstack-kanban in WrongStack/WrongStack) into .claude/skills/wrongstack-kanban in your project. Claude Code loads it when a task matches its description.

How do I install Wrongstack Kanban in Codex?

Run `npx skills add WrongStack/WrongStack --skill wrongstack-kanban -a codex`. Or copy the skill folder (packages/core/skills/wrongstack-kanban in WrongStack/WrongStack) into .agents/skills/wrongstack-kanban in your project. Codex loads it when a task matches its description.

Can I use Wrongstack Kanban in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WrongStack/WrongStack --skill wrongstack-kanban -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wrongstack-kanban, .gemini/skills/wrongstack-kanban, .github/skills/wrongstack-kanban and .opencode/skills/wrongstack-kanban in your project.

What does Wrongstack Kanban need to run?

SKILL.md names no scripts, command-line tools or credentials: Wrongstack Kanban is instructions for the agent only.

Does Wrongstack Kanban access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Wrongstack Kanban safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Wrongstack Kanban use?

Wrongstack Kanban is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wrongstack Kanban use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Wrongstack Kanban?

Skills that share tags, products or a category with Wrongstack Kanban: Kanban (iii-hq/workers, 113 stars), Kanban Heartbeat (cyanluna-git/cyanluna.skills, 183 stars), Frappe Impl UI Components (Impertio-Studio/Frappe_Claude_Skill_Package, 187 stars) and Worklog Sync (cyanluna-git/cyanluna.skills, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wrongstack Kanban?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 368 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 6, 2026.

Source: WrongStack/WrongStack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.