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/test-kanban-md/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/test-kanban-md)<a href="https://agentmods.dev/skills/antopolskiy/kanban-md/test-kanban-md"><img src="https://agentmods.dev/badge/skills/antopolskiy/kanban-md/test-kanban-md/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/test-kanban-md"><img src="https://agentmods.dev/badge/skills/antopolskiy/kanban-md/test-kanban-md.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 | $0.00083 | $0.00631 |
| Opus 5.5 | $0.00033 | $0.00252 |
| Sonnet 5.5 | $0.00017 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
test-kanban-md 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test kanban-md
Choose the smallest fast feedback loop while developing, then widen verification in proportion to the change before declaring it complete.
Required discipline
- Fix bugs with test-driven development: first reproduce the exact failure in a test and confirm it fails for the expected reason, then implement the fix.
- Match the test layer to the behavior. Prefer package tests for internal logic, command tests for CLI wiring, E2E tests for complete binary workflows, and TUI behavioral or snapshot tests for rendered interaction.
- Run focused tests during implementation, the affected package suite after the change, and the full suite before completing production-code work.
- Run lint after Go changes and resolve findings introduced by the change.
- Update golden files only after confirming the new rendering is intended, then inspect the resulting diff rather than accepting it blindly.
- Report the exact commands run and distinguish passing checks, known baseline failures, and checks that were not run.
Bug-fix loop
- Identify the affected package or interface and study nearby test patterns.
- Add the narrowest test that reproduces the reported behavior.
- Run that test and confirm the pre-fix failure is meaningful.
- Implement the smallest sufficient fix.
- Run the reproducer again and confirm it passes.
- Run the affected package or E2E suite.
- Run the full repository tests and lint.
- Review snapshots, generated files, and the final diff for unintended changes.
Do not weaken an assertion merely to make a failing test pass. If the expected behavior is unclear, resolve that product decision before encoding it.
Common verification commands
# One test or package during development
go test ./path/to/package -run TestName -count=1
go test ./path/to/package -count=1
# Repository-wide checks
go test ./...
golangci-lint run ./...
# Full branch validation used by the repository
make precommit
Use make precommit before integration when the change warrants the full build,
race-enabled coverage, E2E, lint, and clean-worktree checks. If it fails because
of a pre-existing baseline, verify the current diff separately and report the
baseline precisely; do not silently present a partial check as a full pass.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 72 lines · 83 tokens per session scan A b26a1077abb3
test-kanban-md is a skill published in the GitHub repository antopolskiy/kanban-md (226 stars, last pushed 23d ago), licensed MIT. It adds 83 tokens to every session and 631 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
swallowtail-qa
Playtest Godot games and exported builds, capture frame spikes, compare QA baselines, and produce Swallowtail branded reports. Use for release QA and reusable game-specific test scenarios, not routine implementation-only unit tests.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
winui-ui-testing
Write and run automated UI tests for Windows desktop apps (WinUI 3, WPF, WinForms, Win32) with the winapp ui harness: one batch script, assertions, input, file pickers, dialogs, screenshots, locally or in Windows Sandbox. Use when asked for UI tests or to verify a feature end to end.