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 srinitude/skills --skill figma-code-connect-design-systemgit clone --depth 1 https://github.com/srinitude/skillsWrote 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/srinitude/skills/figma-code-connect-design-system)<a href="https://agentmods.dev/skills/srinitude/skills/figma-code-connect-design-system"><img src="https://agentmods.dev/badge/skills/srinitude/skills/figma-code-connect-design-system/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/srinitude/skills/figma-code-connect-design-system"><img src="https://agentmods.dev/badge/skills/srinitude/skills/figma-code-connect-design-system.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 | $0.00105 | $0.03922 |
| Opus 5 | $0.00053 | $0.01961 |
| Sonnet 5 | $0.00021 | $0.00784 |
| Haiku 4.5 | $0.00011 | $0.00392 |
Grade A, and why
figma-code-connect-design-system 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Code Connect design system
Create or update one coherent design system from the product truth available in a FigJam board, PRD, image, existing Figma file or library, and codebase. Keep design, code, Code Connect, evidence, permissions, and change effects explicit so no generated suggestion is mistaken for a production change.
Commands
| Command | Result |
|---|---|
help |
Explain inputs, outputs, permissions, commands, and stop conditions without changing anything. |
plan <inputs> [--mode create|update|auto] |
Inspect sources, choose create or update, inventory screens, route capabilities, and write only an authorized run ledger. |
run <inputs> [--mode create|update|auto] |
Execute the approved workflow, harden the hierarchy from tokens upward, and maintain Code Connect after each primitive is ready. |
validate <run-or-target> |
Re-read current repository, Figma, visual, mapping, and lineage state without adding new scope. |
resume <run-ledger> |
Reconstruct current state, invalidate stale proof, and continue from the first unproved dependency. |
refresh-sources |
Compare the package baseline with current first-party specifications, schemas, docs, repository, package registry, and changelog; return a drift report. |
After mise run validate confirms package shape, read the matching worked file in examples/ before each command. Read examples/failure-missing-authority.md when any write, publish, delete, or source authority is unclear.
What ships with it
60 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.
- .github/workflows/ci.yml 423 B
- assets/capability-contracts.json 4.4 KB
- assets/code-connect-mechanisms.json 11 KB
- assets/decision-records.json 4.0 KB
- assets/eval-case-template.json 392 B
- assets/file-manifest.json 2.4 KB
- assets/improvement-contract.json 1.9 KB
- assets/invocation-receipt-template.json 261 B
- assets/mise-primitives-catalog.json 2.0 KB
- assets/mise-primitives.json 3.3 KB
- assets/primitive-lifecycle.json 5.6 KB
- assets/run-contract.json 4.2 KB
- assets/source-manifest.json 2.3 KB
- assets/use-case-contract.json 29 KB
- evals/cases.json 9.5 KB
- evals/contract.md 1.4 KB
- evals/evals.json 11 KB
- evals/manifest.json 476 B
- evals/rubric.md 1.3 KB
- evals/source-lineage.json 18 KB
- evals/speed-budgets.json 355 B
- evals/trigger-cases.json 1.6 KB
- evals/trigger-queries.json 1.5 KB
- examples/failure-missing-authority.md 729 B
- examples/help.md 523 B
- examples/plan.md 616 B
- examples/refresh-sources.md 558 B
- examples/resume.md 663 B
- examples/run.md 1.0 KB
- examples/validate.md 357 B
- mise.toml 4.8 KB
- references/capability-routing.md 8.6 KB
- references/code-connect.md 14 KB
- references/decisions.md 2.1 KB
- references/design-system-lineage.md 9.1 KB
- references/generation-contract.md 5.4 KB
- references/operating-contract.md 5.8 KB
- references/resource-and-experiment-design.md 2.0 KB
- references/source-boundary.md 3.6 KB
- references/use-case-specificity.md 2.4 KB
- references/validation-and-recovery.md 8.0 KB
- scripts/build_factory_policy_assets.py 8.9 KB runs code
- scripts/build_package_records.py 2.2 KB runs code
- scripts/check_code_rules.py 4.1 KB runs code
- scripts/check_evals.py 4.3 KB runs code
- scripts/check_factory_policy.py 2.0 KB runs code
- scripts/check_placeholders.py 3.4 KB runs code
- scripts/lib/agentic_request.py 5.2 KB runs code
- scripts/lib/comparison_validation.py 4.1 KB runs code
- scripts/lib/factory_checks.py 7.5 KB runs code
- scripts/lib/factory_graph.py 2.3 KB runs code
- scripts/lib/factory_improvement.py 1.9 KB runs code
- scripts/lib/factory_records.py 5.1 KB runs code
- scripts/lib/integrated_validation.py 11 KB runs code
- scripts/lib/render_validation.py 2.7 KB runs code
- scripts/lint_writing.py 7.3 KB runs code
- scripts/new_run.py 3.6 KB runs code
- scripts/run_agentic_request.py 1.5 KB runs code
- scripts/skill_info.py 1.5 KB runs code
- scripts/sync_mise_primitives.py 3.7 KB runs code
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 Changed · +1 lines 6bbbfe32dbfe
- 5d ago First seen · 153 lines · 105 tokens per session scan A 0d658bb12f9c
figma-code-connect-design-system is a skill published in the GitHub repository srinitude/skills (2 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 3,922 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
core-components
Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
popular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
hypnotic-pattern
Hypnotic Pattern mesmerizes everyone who looks at it. The real-world version is attention design: loading animations, progress indicators, onboarding flows, and visual patterns that keep users oriented and engaged during a bounded experience. The line between helpful focus and addictive capture is the central design…