TypingMindTypingMindThe best frontend for AI
Kanban Flow Stinger logo

Kanban Flow Stinger

Organization
legioncodeinc
kanban-flow-stinger

Improve Kanban flow. Use for WIP limits, cycle time, throughput, Little's Law, board design, or cumulative flow. Read guides/ for the decision path.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namekanban-flow-stinger
Stars
94
Forks
44
Bundled files
9
LicenseAGPL-3.0-or-later
Links
Skill sourceRepository
  • 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.

  • 9 bundled files

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

  • Open source

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

Installation

Install the Kanban Flow Stinger 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/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/kanban-flow-stinger
  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/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/business-and-product-tools/skills/kanban-flow-stinger .claude/skills/kanban-flow-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kanban Flow Stinger 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 Flow Stinger 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 Flow Stinger 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-flow Stinger

The arsenal for kanban-flow-wasp-drone. This skill encodes the Kanban Method from the Toyota Production System lineage through David J. Anderson's 2010 formalization to the 2026 practitioner landscape, with hands-on implementation guidance for the tools teams actually use.

Master index: read SKILL.md (this file) first to orient. Then open the guide for the specific domain the user's question touches. All factual claims in the guides trace to files in research/.

When this stinger applies

Activate on any of:

  • "Our WIP keeps climbing" / "team has too much in flight"
  • "We can't predict when work will finish"
  • "How do I measure cycle time?" / "what's our throughput?"
  • "Apply Little's Law to our board"
  • "Help us design our Kanban columns" / "we need WIP limits"
  • "Should we use Kanban or Scrum?"
  • "How do I set up Kanban in Linear / Jira / GitHub Projects?"
  • "Why is our flow efficiency so low?"
  • "kanban-flow-wasp-drone" invoked directly

Do NOT activate for:

  • Sprint planning, retrospectives, or velocity measurement (Scrum; no peer Drone today)
  • CI/CD deployment pipeline design (devops-wasp-drone)
  • Prometheus / Grafana / Datadog metric dashboards for infrastructure (monitoring stack)
  • Custom Kanban app development in React or Python (hand off after designing the board)

Guardrails (from SUBAGENT CRITICAL DIRECTIVES)

These are non-negotiable before proceeding with any recommendation:

  1. Surface WIP limits first. Without WIP limits, what you are looking at is a task list, not Kanban. Every recommendation starts here. Source: research/internal/command-brief-summary.md (source-repository research, not shipped with the plugin).

  2. Never set a WIP limit without data. Arbitrary limits ("just use 3") create false confidence. Ask for historical WIP or throughput data. If none exists, explain how to gather two weeks of data first. See guides/01-wip-limits.md. Source: research/external/2026-05-20-wip-limits-agile-flow-consulting.md (source-repository research, not shipped with the plugin).

  3. Always distinguish cycle time from lead time. Define which clock starts and ends for each. Conflation is the most common flow-metric error. See guides/02-flow-metrics.md. Source: research/external/2026-05-20-flow-metrics-definitions-cylenivo.md (source-repository research, not shipped with the plugin).

  4. Apply Little's Law only in steady state. If >20% of WIP is blocked or the expedite queue is active, flag non-steady-state before running L = λW. See guides/03-littles-law.md. Source: research/external/2026-05-20-littles-law-abstract-algorithms.md (source-repository research, not shipped with the plugin).

  5. Respect the Toyota lineage without dogmatism. Kanban evolved from TPS, but software teams are not car factories. Use the theory to explain why practices work, not to shame adaptation.

  6. Distinguish the Kanban Method from a Kanban board. A Scrum team using a board is NOT practising Kanban (no explicit policies, no WIP limits, no cadence meetings). Correct this politely but clearly.

  7. Confirm the target tool before prescribing configuration. Linear (no native WIP limits), Jira (swimlane WIP bug), and GitHub Projects (visual-only limits) all behave differently. See guides/08-tool-implementation.md. Source: research/external/2026-05-20-tool-wip-limits-honest-review.md (source-repository research, not shipped with the plugin).

Guide map

Open the guide that matches the user's question. Each guide is self-contained and cites its research sources.

GuideWhen to open
guides/00-kanban-theory.mdUser asks about the Kanban Method's foundations, Toyota lineage, or the six general practices
guides/01-wip-limits.mdWIP limit setting, enforcement, Little's Law connection to cycle time
guides/02-flow-metrics.mdCalculating cycle time, lead time, throughput, flow efficiency, WIP age
guides/03-littles-law.mdL = λW application, steady-state assumptions, three-variable dial, forecasting
guides/04-cumulative-flow-diagram.mdReading the CFD, seven anti-pattern shapes, leading vs lagging indicators
guides/05-board-design.mdColumn structure, explicit policies, blocker notation, replenishment
guides/06-class-of-service.mdFour tiers (Standard, Fixed-Date, Expedite, Intangible), queue-bypass rules
guides/07-kanban-vs-scrum.mdDecision framework, Scrumban hybrid, migration path
guides/08-tool-implementation.mdLinear, Jira, GitHub Projects: exact configuration steps and known bugs

Template map

Use these stubs to produce deliverables for the user:

TemplateUse for
templates/board-design-spec.mdColumn / WIP limit / policy / done-definition table
templates/class-of-service-card.mdFour-tier service class reference card
templates/flow-metrics-report.mdComputed metrics summary with interpretation
templates/littles-law-forecast.mdWIP-scenario forecast table

Example map

ExampleShows
examples/wip-limit-setup-happy-path.mdEnd-to-end WIP limit implementation from raw throughput data to Jira configuration
examples/cycle-time-diagnosis.mdDiagnosing a cycle-time spike using flow metrics and CFD shape

Key benchmarks (2026 practitioner data)

These numbers come from research/external/2026-05-20-value-stream-metrics-axify.md (source-repository research, not shipped with the plugin) and should be cited when calibrating expectations:

  • Typical software team flow efficiency: 5-20% (15-20% is mature/WIP-limited; single-digits is common in unoptimized teams)
  • Elite cycle time (p75): 1.8 days
  • Elite lead time: sub-24 hours
  • Scrumban adoption: 45% of Scrum teams migrate to Scrumban after 2-3 years (State of Agile 2026)
  • WIP limit ROI case study: a 12-person team achieved 42% cycle time reduction (p85 62 days → 36 days) by implementing throughput-derived WIP limits

Tool WIP limit status (2026)

From research/external/2026-05-20-tool-wip-limits-honest-review.md (source-repository research, not shipped with the plugin), confirmed April 2026:

ToolNative WIP limit enforcementNotes
LinearNoneGraphQL API workaround available; soft enforcement via naming convention
Jira SoftwareColumn limits only (not per-swimlane)Swimlane WIP count bug: Atlassian has not fixed; see guides/08-tool-implementation.md
GitHub ProjectsVisual-only (no enforcement)Column limit shows count in red but does not block card addition
Azure DevOps BoardsColumn limits with enforcementMost capable WIP enforcement of the four tools
TrelloNone nativePower-Up plugins available

Open questions (for user decision before next stinger refresh)

Two questions from research/research-summary.md remain unresolved:

TODO: Monte Carlo for small teams (< 5 people): Vacanti/ActionableAgile has not published 2025-2026 guidance specific to small sample sizes. Until resolved, guides/03-littles-law.md advises 15-20 data points minimum and directs users to ActionableAgile Analytics tooling.

TODO: Kanban vs Shape Up formal comparison: No 2025-2026 comparison article found. guides/07-kanban-vs-scrum.md notes Shape Up as a distinct alternative with a brief first-principles contrast.

Command Brief: ai-tools/command-briefs/kanban-flow-wasp-drone-command-brief.md Research: research/ (17 files, normal depth, 2025-11 to 2026-05) Forged: 2026-05-20 by stinger-forge via gods-hand slot-04

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 Flow Stinger AI skill do?

Improve Kanban flow. Use for WIP limits, cycle time, throughput, Little's Law, board design, or cumulative flow. Read guides/ for the decision path.

Why use Kanban Flow Stinger on TypingMind?

Because you install it once and use it with any model. Kanban Flow Stinger 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 Flow Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/business-and-product-tools/skills/kanban-flow-stinger. 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 Flow Stinger?

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 Flow Stinger?

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

Is the Kanban Flow Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later 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.

Related AI Skills

View all
NousResearch logo

Grok

NousResearch
OrganizationPopular

Delegate coding to xAI Grok Build CLI (features, PRs).

53.5K
250.4K
Instructions
View
NousResearch logo

Setup Wizard Generator

NousResearch
OrganizationPopular

Generate a bash wizard guiding a human through manual setup.

53.5K
250.4K
1 files
View
NousResearch logo

Mcp Oauth Remote Gateway

NousResearch
OrganizationPopular

Manual OAuth for remote MCP servers on headless gateways.

53.5K
250.4K
2 files
View
NousResearch logo

Serving Llms Vllm

NousResearch
OrganizationPopular

vLLM: high-throughput LLM serving, OpenAI API, quantization.

53.5K
250.4K
4 files
View

Set up your own AI workspace now

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