mcp-tool-surface SKILL.md skillA
mcp-tool-surface from kamiazya/whiteboard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kamiazya/whiteboard/mcp-tool-surface@git:20261002.5a9037fPins git:20261002.5a9037f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kamiazya/whiteboard
- Path
.claude/skills/mcp-tool-surface/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261002.5a9037f, committed Oct 2, 2026
- First version recorded
- Sep 10, 2026
- Size
- 22,687 bytes
- Repository stars
- 10
- License
- Apache-2.0
How to change the whiteboard MCP tool table — rename, re-describe, reshape, add, consolidate or retire a tool — with the two scoreboards and the LLM-driven lane that ADR-0031 makes the evidence. Use before touching a tool's name, description, input schema, annotations or existence under packages/server-core/src/tools/** or packages/mcp-server/src/server/mcp/**, when a consolidation is proposed, when someone says "too many tools", or when adding an eval task. Not for the daemon's HTTP routes or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# The tool surface is judged by an instrument A tool definition is read by a model on every turn of every conversation that has this server attached, and a model asked to do something reads the table before it reads the document. So a change to the table is not judged by whether the tests pass — they pass either way — but by four numbers nobody sees in the diff: what the table costs to read, how much of it explains itself, what an errand costs in calls, and whether a real model still completes the errands. The criteria are [ADR-0031](../../../docs/contributing/adr/0031-tool-surface-criteria.md) §1 (C1–C14, each tagged with the rung that checks it); this skill is the procedure. The count is not a criterion. The last consolidation would have steered by it, and the count cannot see the two largest debts the instrument found on its first run: one tool being 45% of everything the model reads, and 299 of 324 parameters undescribed. ## The ladder, and which rung a change runs | rung | what | command | runs | |---|---|---|---| …
Read the whole file at its exact version.
How to install
mdr add kamiazya/whiteboard/mcp-tool-surface@sha256:00691a5854a4b216The line at the top of this page pins the label git:20261002.5a9037f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_npwm7nqph4thesvf)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 10, 2026 and Oct 2, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261002.5a9037f latest | 2026-10-02 | 5a9037f | 22,687 B | A | view · diff |
| git:20261002.3e13332 | 2026-10-02 | 3e13332 | 22,691 B | A | view · diff |
| git:20260916.7a55f38 | 2026-09-16 | 7a55f38 | 22,631 B | A | view · diff |
| git:20260913.b10855f | 2026-09-13 | b10855f | 21,830 B | A | view · diff |
| git:20260913.99668c9 | 2026-09-13 | 99668c9 | 19,663 B | A | view · diff |
| git:20260912.ebd6df5 | 2026-09-12 | ebd6df5 | 18,252 B | A | view · diff |
| git:20260910.514441f | 2026-09-10 | 514441f | 16,253 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (22687 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kamiazya/whiteboard · 10 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_npwm7nqph4thesvf GET https://markdownregistry.com/api/v1/resolve?ref=kamiazya/whiteboard/mcp-tool-surface GET https://markdownregistry.com/api/v1/blob/00691a5854a4b216de5d766be579a1abd29e8c396c77b0025fe086816e7a8ad8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.