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/kamiazya/whiteboard/auditing-workspacesnpx skills add kamiazya/whiteboard --skill auditing-workspacesgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/auditing-workspaces)<a href="https://agentmods.dev/skills/kamiazya/whiteboard/auditing-workspaces"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/auditing-workspaces.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 5.1 | $0.00060 | $0.01134 |
| Opus 5 | $0.00030 | $0.00567 |
| Sonnet 5 | $0.00012 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
auditing-workspaces 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 3d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auditing-workspaces
List a workspace's documents, then use the spatial ones' scene digests to judge which look empty or abandoned. There is no server-side audit endpoint — this skill is a recipe for composing the regular document tools toward that end, nothing more.
For the main drawing workflow, see the drawing-visuals skill in skills/drawing-visuals/SKILL.md.
When To Use It
- When a workspace has been in heavy use and you want a sense of what is in it before adding more
- When you want to check for a likely-duplicate path before calling
wb_document_create - When you want to know whether a spatial document is worth opening without rendering it
Execution Flow
Step 1: List The Workspace's Documents
wb_document_list({ workspaceId })
Returns { documents: [{ documentId, path, name?, kind?, updatedAt?, shadowed? }] } — placement only, no content. An unknown
workspaceId is an error here, not an empty list, so a typo reads as a failure rather than "nothing
found."
Step 2: Classify, Then Sample Each Document
Step 1's listing carries no kind, and wb_document_get is the only tool that reports one — so
classification comes first, and it costs one wb_document_get per document:
wb_document_get({ workspaceId, documentId })
// markdown -> { kind: "markdown", content: "...", frontmatter: {...} } (the body, directly)
// spatial -> { kind: "spatial", content: "..." } (full JSON Canvas payload)
// no recorded kind -> throws a "no recorded kind" error — itself a signal worth reporting
Read the kind before reading the content. A spatial read refuses a document it knows to be
markdown rather than reporting its containers as empty, so it cannot silently answer "nothing
here" about a document full of prose — but it also cannot tell you the kind of a document you have
not identified yet. wb_document_get is what establishes that.
Once a document is KNOWN spatial (from wb_document_get's kind, or because this session created
it), wb_canvas_snapshot is the cheap re-probe for later passes — node text, geometry and lock
state without the untruncated JSON Canvas payload:
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.
- 3d ago Changed 1c85f4e73585
- 6d ago First seen · 110 lines · 60 tokens per session scan A 69783ec5b823
auditing-workspaces is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,134 once invoked, about $0.0003 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.