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 Snowflake-Labs/cocoplus --skill cocosketchgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/cocosketch)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/cocosketch"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocosketch/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/snowflake-labs/cocoplus/cocosketch"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocosketch.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 | $0.00020 | $0.02105 |
| Opus 5 | $0.00010 | $0.01052 |
| Sonnet 5 | $0.00004 | $0.00421 |
| Haiku 4.5 | $0.00002 | $0.00211 |
Grade A, and why
cocosketch 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 5d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CocoSketch — Visual Artifact Generation Pipeline
Core Principle
Diagram quality requires a pipeline, not a single prompt. The AI generates XML; deterministic scripts validate and repair. Never skip validation or repair steps.
Seven-Step Pipeline (ALL modes)
Step 1: Resolve style preset
Step 2: Check draw.io CLI availability (resolve binary once, use verbatim)
Step 3: Plan layout — shapes, relationships, groups; run cocosketch/sketch-autolayout for >15 nodes
Step 4: Generate draw.io XML → run cocosketch/sketch-validate → STOP pipeline if FAIL
Step 5: Export PREVIEW PNG (NO -e flag) capped at 2000px
Step 6: Self-check preview via vision — auto-fix overlaps/clipped labels (max 2 rounds)
Step 7: Export FINAL PNG (WITH -e flag) → run cocosketch/sketch-repair → deliver to developer
NEVER skip Steps 4 or 7. NEVER add -e to Step 5. NEVER omit -e from Step 7.
Step 1 — Resolve Style Preset
Check ~/.cocoplus/sketch-styles/ first, then .cortex/sketch/styles/built-in/.
Available built-in styles: default, corporate, handdrawn.
Default: default.json. Load and apply to all generated cells.
Step 2 — Check draw.io CLI
Try in order: drawio --version, draw.io --version, OS-specific paths.
Resolve binary name ONCE. Store as DRAWIO_BIN. Use DRAWIO_BIN verbatim in Steps 5 and 7.
Fallback chain (if draw.io unavailable):
- Generate Mermaid markup → write
<name>.mmd, inform developer - If Mermaid not applicable: deliver raw
.drawioXML with open-in-browser instructions
Step 3 — Plan Layout
- Direction: LR for sequences/pipelines, TB for hierarchies/schemas
- For >15 nodes: run
invoke cocosketch/sketch-autolayout <input.json> <layout.json> - For ≤15 nodes: hand-place coordinates with reasonable spacing (120px wide × 60px tall, 50px H-gap, 40px V-gap)
- Groups: use swimlane cells to visually cluster related nodes
Step 4 — Generate XML + Validate
Required XML structure:
<mxGraphModel>
<root>
<mxCell id="0" />
<mxCell id="1" parent="0" />
<!-- shape cells: parent="1", unique id each -->
</root>
</mxGraphModel>
Run: invoke cocosketch/sketch-validate <file.drawio>
If FAIL: stop immediately. Report structural errors. Do not proceed to Step 5.
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.
- 5d ago First seen · 173 lines · 20 tokens per session scan A 88ecd7baab52
cocosketch is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 2,105 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
cad-skill
Generate interior design planning artifacts, 2D SVG floorplans, BOM outputs, analysis boards, and renovation image sets from structured requirements. Use for staged interior-design work that moves through plan, 2D drafting, BOM, and image outputs.
flow-skill
Generate, edit, validate, and bundle draw.io or diagrams.net diagrams in XML form. Use for new diagrams, local XML edits, shape-library diagrams, truncated XML continuation, and local image export.
drawio-skill
Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams. Use when the user explicitly requests draw.io/diagrams.net, needs a polished architecture, ERD, UML, sequence, C4, SysML, BPMN, network, swimlane, ML, or infrastructure diagram, wants code/IaC/SQL/OpenAPI converted into a diagram, or…
decocms-ui
Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…
bare-eval
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.