Grida is an open-source graphics workspace that combines an infinite canvas editor, SVG tools, a database and CMS, and forms. Designers and developers use it to create, import, render, and manage visual documents and connected data, while the catalogue add-ons support its workflows.
Borrowing it
Nothing to install: this file belongs to gridaco/grida. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gridaco/grida/main/.agents/skills/docs-svg-kit/SKILL.mdgit clone --depth 1 https://github.com/gridaco/gridaWrote 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/gridaco/grida/docs-svg-kit)<a href="https://agentmods.dev/skills/gridaco/grida/docs-svg-kit"><img src="https://agentmods.dev/badge/skills/gridaco/grida/docs-svg-kit/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/gridaco/grida/docs-svg-kit"><img src="https://agentmods.dev/badge/skills/gridaco/grida/docs-svg-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 31 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Prompt Injection · line 65 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Prompt Injection · line 101 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 121 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00145 | $0.05025 |
| Opus 5.5 | $0.00058 | $0.02010 |
| Sonnet 5.5 | $0.00029 | $0.01005 |
| Haiku 4.5 | $0.00015 | $0.00502 |
Grade A, and why
docs-svg-kit 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 2mo 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs SVG Kit
A snippet library for drawing SVG figures embedded in Grida docs. Canvas user docs are the kit's first consumer; the same primitives and conventions are meant to carry over to any product's docs as they adopt SVG figures.
First consumer / companion:
docs-canvas. Use that skill for the prose,
this one for the visuals embedded inside it.
Why SVG, not a screenshot
Screenshots are easy to capture but expensive over time:
- Stale by default. UI shifts; the screenshot keeps showing the old state until someone re-captures it. There is no diff, no warning, no test that fails.
- Repo weight. Every re-capture is a new binary blob in git history. WebP at 960 × 960 is ~30–80 KB each; PNG is multiples of that. Across years of captures it compounds, and old blobs never leave history.
- Frozen in time. A screenshot shows one moment of one configuration. A diagram explains the rule across configurations.
So: when SVG can carry the meaning, prefer SVG. SVGs are text — diff-able, hand-editable, version-controlled like code. Reserve screenshots for cases where the actual rendered chrome (real fonts, real pixels) is the point.
When to draw an SVG figure
Reach for a custom SVG when a screenshot can't carry the story alone:
- A gesture (the clickable target isn't visible at rest — double-click, drag, hover).
- A before / after that needs the two states side-by-side.
- A rule that hinges on an invisible anchor or pivot (alignment, snapping, hit-testing).
If a single screenshot of the editor would communicate the whole point, use a screenshot. Don't redraw real UI in SVG when you don't have to.
Hard constraints
These are baked into the kit. Don't fight them.
- Inline
<style>only. Never reference an external stylesheet. Docusaurus serves docs SVGs via<img src>, which sandboxes the SVG: external CSS, scripts, and cross-file<use href>are all blocked. - No cross-file
<use>. Every reused fragment must physically live inside the SVG's own<defs>. Copy fromsnippets/, don't import. - Self-contained = SEO-safe. Inline-styled SVGs are indexed as images. Inline React components in MDX are not — they become HTML.
- Output size: 960 × 960. The viewport for all figures, matching
docs/AGENTS.mdscreenshot conventions. UseviewBox="0 0 960 960" width="960" height="960". - Watermark every kit-produced SVG (see below).
- No emojis. No marketing voice. Same neutral tone as the prose.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 266 lines · 145 tokens per session scan A a76349fc7b27
docs-svg-kit is a skill published in the GitHub repository gridaco/grida (2,693 stars, last pushed 11d ago), licensed Apache-2.0. It adds 145 tokens to every session and 5,025 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
explorer
Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.
database-engineer
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults" !cat .forgewright/codebase-context.md…
database-design-patterns
Schema design, normalization decisions, indexing strategies, and migration safety for relational databases. Use when designing tables, choosing between normalize vs denormalize, selecting index types, planning zero-downtime migrations, or setting up connection pooling. Activate on "schema design", "normalization"…
database
Relational database authority — PostgreSQL, async ORM (SQLAlchemy 2 / asyncpg), Alembic schema migrations, Supabase Python and JS clients, query optimisation, index strategy, connection pooling, transaction patterns, and bulk operations across Python and Node stacks.
whodb
Work with WhoDB platform hosts and project resources via MCP, including multiple environments, or query databases directly in database-only MCP mode.
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.