Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/darecstowell/scratchboard/scratchboardnpx skills add darecstowell/scratchboard --skill scratchboardgit clone --depth 1 https://github.com/darecstowell/scratchboardWrote 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/darecstowell/scratchboard/scratchboard)<a href="https://agentmods.dev/skills/darecstowell/scratchboard/scratchboard"><img src="https://agentmods.dev/badge/skills/darecstowell/scratchboard/scratchboard.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01396 |
| Opus 5 | $0.00041 | $0.00698 |
| Sonnet 5 | $0.00016 | $0.00279 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
scratchboard 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection finds the tickets, picks a preset, and proposes lanes and facets on its own, so the three jobs below are the parts that take judgement or code.
You write two files, scratchboard.json and scratchboard.parser.mjs, both at the repo root,
and you ask the user before each. None of the three jobs changes a ticket.
Moving a card is the other job and it needs no config. A lane that matches on a field is moved by writing that field in the ticket, one line, in the vocabulary the repo already uses. The board never writes it, because the board is read-only.
The vocabulary a card is moved with
Read the repo's own values first, from its lanes in scratchboard.json and from the tickets
themselves, and write what is already there. The list below is the vocabulary the skills speak
in, which is what a repo that has none of its own should use.
| Value | Means |
|---|---|
needs-triage |
A maintainer needs to evaluate this ticket |
needs-info |
Waiting on the reporter for information |
ready-for-agent |
Fully specified, ready for an agent working alone |
ready-for-human |
Needs a human to implement it |
wontfix |
Will not be actioned |
done |
Shipped and verifiable in the history |
The first five are the canonical triage roles. done is scratchboard's own terminal state,
because the five are a triage queue rather than a lifecycle. A repo may carry values outside both
sets, as this one carries deferred for work someone looked at and chose later. Those pass
through untouched, take their lane from local config, and are never rewritten into a value from
the table.
The reader spec is docs/local-markdown-spec.md in the
scratchboard repository.
It names every value the board recognizes, the file shapes it reads, and what happens to input it
does not recognize. Read it rather than guessing, and do not restate it in a repo's own docs.
1. Locate the tickets
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.
- 4d ago First seen · 120 lines · 81 tokens per session scan A 770b85f192d5
scratchboard is a skill published in the GitHub repository darecstowell/scratchboard (6 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,396 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
kanban-board
To do / In progress / In review / Done 四列, 卡片 + 头像 + 泳道.
kanban-tui
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the ktui command is not available, but uv is available utilize uvx kanban-tui…
codekanban-cli
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command. Use when the user wants to create, inspect, control, watch, or continue CodeKanban AI work from a project path, project ID, or project name without relying on repository-local helper scripts. Prefer…
kanban-md
Manage project tasks using kanban-md, a file-based kanban board CLI. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or…
kanban-based-development
Autonomous, parallel-safe development workflow using kanban-md. Use when the user asks to work through tasks, do kanban-based development, or when multiple agents need to coordinate work on the same codebase. Optimized for explicit handoffs and a "defer to user" protocol when human intervention is required.
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.