Borrowing it
Nothing to install: this file belongs to gablabelle/mcp-kanban. 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/gablabelle/mcp-kanban/main/.claude/skills/kanban-start/SKILL.mdgit clone --depth 1 https://github.com/gablabelle/mcp-kanbanWrote 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/gablabelle/mcp-kanban/kanban-start)<a href="https://agentmods.dev/skills/gablabelle/mcp-kanban/kanban-start"><img src="https://agentmods.dev/badge/skills/gablabelle/mcp-kanban/kanban-start/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/gablabelle/mcp-kanban/kanban-start"><img src="https://agentmods.dev/badge/skills/gablabelle/mcp-kanban/kanban-start.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 | $0.00046 | $0.00840 |
| Opus 5.5 | $0.00018 | $0.00336 |
| Sonnet 5.5 | $0.00009 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
kanban-start 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 2mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Through Kanban Tickets
You are executing planned work from the mcp-kanban board. Move tickets through columns and update them as you work.
Step 1: Discover the board
Use mcp__mcp-kanban__list_columns to get the column IDs. Identify:
- The "in progress" column (for active work)
- The "review" column (if it exists, for completed-but-not-verified work)
- The "done" column (for finished work)
Use mcp__mcp-kanban__list_tickets to see all tickets and find which ones are ready to work on (in Backlog or Todo).
Step 2: Pick the next ticket
If $ARGUMENTS specifies a ticket or story, start with that. Otherwise, pick the highest-priority story that hasn't been started yet.
Use mcp__mcp-kanban__get_ticket to read the full ticket details including subtasks.
Step 3: Move the story to In Progress
Use mcp__mcp-kanban__move_ticket to move the parent story to the "in progress" column. This signals on the board that work has begun.
Step 4: Work through each subtask
For each subtask in the story:
- Before starting: Move the subtask to "in progress" with
mcp__mcp-kanban__move_ticket - Do the work: Implement the changes — read files, write code, run tests, etc.
- Update the ticket: Use
mcp__mcp-kanban__update_ticketto add implementation notes to the subtask description — what was done, what files were changed, any decisions made - Mark complete: Use
mcp__mcp-kanban__complete_subtaskto move the subtask to Done
Step 5: Complete the story
Once all subtasks are done:
- Use
mcp__mcp-kanban__update_ticketto update the parent story's description with a summary of what was implemented - Move the story to "review" or "done" column with
mcp__mcp-kanban__move_ticket
Step 6: Continue or stop
After completing a story, check if there are more stories to work on:
- If yes, ask the user: "Story complete. Ready to move on to the next one?"
- If no more stories, report: "All planned work is complete."
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.
- 2mo ago First seen · 60 lines · 46 tokens per session scan A 62f1c2669824
kanban-start is a skill published in the GitHub repository gablabelle/mcp-kanban (4 stars, last pushed 8mo ago), licensed MIT. It adds 46 tokens to every session and 840 once invoked, about $0.0002 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 2026-08-31.
kanban-start compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kanban-startgablabelle/mcp-kanban | Skill | 4 | 8mo ago | MIT | A | 46 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |