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 skills add bearlike/Grove --skill collaborating-on-diagramsgit clone --depth 1 https://github.com/bearlike/GroveWrote 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/bearlike/grove/collaborating-on-diagrams)<a href="https://agentmods.dev/skills/bearlike/grove/collaborating-on-diagrams"><img src="https://agentmods.dev/badge/skills/bearlike/grove/collaborating-on-diagrams/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/bearlike/grove/collaborating-on-diagrams"><img src="https://agentmods.dev/badge/skills/bearlike/grove/collaborating-on-diagrams.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 | $0.00068 | $0.01825 |
| Opus 5 | $0.00034 | $0.00912 |
| Sonnet 5 | $0.00014 | $0.00365 |
| Haiku 4.5 | $0.00007 | $0.00183 |
Grade A, and why
collaborating-on-diagrams 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 today.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborating on diagrams
Use Grove's diagram tools for a human-and-agent edit of one existing .drawio
file in a workspace. The file remains the source of truth. Grove does not create
new diagrams, commit changes, publish diagrams, or share them publicly.
This skill is for managed collaboration, not ordinary source editing. Before a managed session exists, use your normal editor or shell. Once it is active, use the diagram tools for every read and write to that file.
Start with the existing file
Open an existing workspace-relative .drawio path. Do not pass an absolute path,
a parent traversal, a symlink, or another file type.
grove_open_diagram(workspace_id="WORKSPACE_ID", path="architecture.drawio")
The open result contains the current XML and its revision. It creates a
collaboration identity for the workspace and is idempotent only for the same
active path. Its diagram.session_id is the identity for later updates and its
diagram.mode is active. Opening another path while one is active is a
conflict: finish the first session with grove_stop_diagram, then open the other
file.
Read the document through Grove before proposing an edit:
grove_read_diagram(workspace_id="WORKSPACE_ID")
Keep the revision returned by the latest successful open, read, or update. Keep
the session identity at diagram.session_id as well. Inspect diagram.mode
before each edit; it is either active or read_only. Do not invent an identity
or reuse one after a stop and reopen.
Preserve draw.io XML
A .drawio file is XML. Managed saves use editable, uncompressed <mxfile> XML.
Do not base64-encode, wrap, flatten, or replace it with an image format.
- Preserve all
<diagram>pages, including pages unrelated to the request. - Preserve existing
mxCellIDs and references. Add stable new IDs only when a new cell genuinely needs one. - Escape XML values correctly, especially
&,<,>, quotes, and label content. Put literal markup in a value only when draw.io's existing shape markup requires it. - Keep the document well-formed. Do not introduce DTDs or entities.
- Make the smallest requested structural change. Do not reformat an unrelated diagram or regenerate its whole model merely because it is XML.
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.
- today First seen · 188 lines · 68 tokens per session scan A d9f787434b16
collaborating-on-diagrams is a skill published in the GitHub repository bearlike/Grove (2 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,825 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 2026-09-17.
Other skills, from other repositories
paseo-help
Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces…
paseo-advisor
Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself.
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
write-detection-rule
This skill teaches Claude Code how to write detection rules for the AI Traffic Control rule engine. Read this before creating or modifying anything in rules/. The full rule schema is Rule in packages/schema/src/zod/rule.ts — it is the source of truth for every field below.
aka-dashboard
Launch the AKA web dashboard in your browser (reads your local store).
aka-health
Show AKA detection activity and local security posture.