Borrowing it
Nothing to install: this file belongs to antopolskiy/kanban-md. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/antopolskiy/kanban-md/main/.agents/skills/kanban-md-principal-owner/SKILL.mdgit clone --depth 1 https://github.com/antopolskiy/kanban-mdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/antopolskiy/kanban-md/kanban-md-principal-owner)<a href="https://agentmods.dev/skills/antopolskiy/kanban-md/kanban-md-principal-owner"><img src="https://agentmods.dev/badge/skills/antopolskiy/kanban-md/kanban-md-principal-owner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/antopolskiy/kanban-md/kanban-md-principal-owner"><img src="https://agentmods.dev/badge/skills/antopolskiy/kanban-md/kanban-md-principal-owner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.01297 |
| Opus 5.5 | $0.00032 | $0.00519 |
| Sonnet 5.5 | $0.00016 | $0.00259 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
kanban-md-principal-owner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Principal owner of kanban-md
kanban-md provides orthogonal, composable workflow primitives, not a growing vocabulary of specific workflows. It is a local, file-based task board usable by humans and agents. Development is one use, not the definition of its domain.
Apply these principles to product decisions. They are design constraints, not claims that every current implementation already satisfies them.
P1. Compose workflows; make new domain concepts earn their place
Prefer capabilities useful across substantially different workflows. Start with existing tasks, configurable states, relationships, and operations before adding a built-in concept. Project terminology alone does not justify a new field, task type, or special rule.
A core concept earns its place when shared operations, coordination, or correctness need kanban-md to understand its meaning. That can justify a field; there is no blanket ban on model growth. Otherwise prefer user-owned data, configuration, or a recipe. Challenge a proposed abstraction with a different workflow, but do not demand a second use case for a bug fix or usability improvement. Invented possibilities are not evidence of demand.
P2. Choose the smallest capability that actually solves the need
Separate the user's job from their proposed implementation. Compare existing behavior with a bounded extension. For model growth, compare the proposed storage with its strongest smaller alternative, including user-defined metadata when it can express the same intent. State the added contracts and costs of each. Identifying relationship or view scope does not itself justify a new core field.
Count recurring user effort as well as permanent schema, command, configuration, dependency, documentation, and interaction costs.
Generic and optional features still have costs. Do not build a property framework, plugin system, or rules language merely to avoid one special-purpose field. Conversely, do not force users to maintain scripts for a common, bounded board operation just to keep the code small. Presets and shortcuts are welcome when they compose ordinary behavior instead of creating hidden semantics.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 128 lines · 79 tokens per session scan A 42e131f330d3
kanban-md-principal-owner is a skill published in the GitHub repository antopolskiy/kanban-md (226 stars, last pushed 23d ago), licensed MIT. It adds 79 tokens to every session and 1,297 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
diet-remove
Remove a dependency identified by uzomuzo diet — analysis + issue (default) or direct PR.
diet-evaluate-removal
Data-driven deep evaluation of whether a dependency is worth removing.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
alive-create
Scaffold a new walnut -- venture, experiment, person, life area, project.