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.
git clone --depth 1 https://github.com/friedbeef1/design-arcWrote 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/plugins/friedbeef1/design-arc/gemini-extension)<a href="https://agentmods.dev/plugins/friedbeef1/design-arc/gemini-extension"><img src="https://agentmods.dev/badge/plugins/friedbeef1/design-arc/gemini-extension/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/plugins/friedbeef1/design-arc/gemini-extension"><img src="https://agentmods.dev/badge/plugins/friedbeef1/design-arc/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
design-arc 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 1mo 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.
What it actually says
{
"name": "design-arc",
"version": "1.5.5",
"description": "Alpha: outcome-led UI journey design for Google Antigravity."
}
What ships with it
42 files beside gemini-extension.json 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.
- assets/design-arc-directory-logo.png 22 KB
- assets/design-arc-directory-logo.svg 726 B
- examples/prompts.md 7.4 KB
- scripts/check_repository_hygiene.py 3.0 KB runs code
- scripts/check-antigravity-runtime-contracts.py 7.6 KB runs code
- scripts/check-claude-state-contracts.py 8.5 KB runs code
- scripts/check-workflow-contracts.py 46 KB runs code
- scripts/compose-design-arc-skills.py 20 KB runs code
- scripts/fixtures/graph-records/contradictory-active-relationships.json 967 B
- scripts/fixtures/graph-records/corrupt.json 70 B
- scripts/fixtures/graph-records/duplicate-ids.json 341 B
- scripts/fixtures/graph-records/incomplete-required-fields.json 406 B
- scripts/fixtures/graph-records/missing-endpoint.json 553 B
- scripts/fixtures/graph-records/reverse-direction-contradictory-active-relationships.json 975 B
- scripts/fixtures/graph-records/unproven-relationship.json 636 B
- scripts/fixtures/graph-records/unsupported-edge-type.json 653 B
- scripts/fixtures/graph-records/unsupported-node-type.json 235 B
- scripts/fixtures/graph-records/unsupported-provenance.json 626 B
- scripts/fixtures/graph-records/unsupported-schema.json 130 B
- scripts/fixtures/graph-records/valid.json 4.2 KB
- scripts/test_repository_hygiene.py 3.3 KB runs code
- scripts/test-antigravity-package.py 3.3 KB runs code
- scripts/test-antigravity-runtime-contracts.py 11 KB runs code
- scripts/test-asset-fidelity-acceptance.py 53 KB runs code
- scripts/test-claude-package.py 5.0 KB runs code
- scripts/test-claude-plugin-install.sh 2.9 KB runs code
- scripts/test-claude-state-contracts.py 11 KB runs code
- scripts/test-design-arc-docs.sh 78 KB runs code
- scripts/test-design-arc-identity.sh 14 KB runs code
- scripts/test-graph-records.py 4.2 KB runs code
- scripts/test-plugin-install.sh 11 KB runs code
- scripts/test-plugin-migration.sh 8.9 KB runs code
- scripts/test-plugin-upgrade-state.py 24 KB runs code
- scripts/test-plugin-upgrade.sh 17 KB runs code
- scripts/test-runtime-visualization-contracts.py 14 KB runs code
- scripts/test-skill-composition.py 7.4 KB runs code
- scripts/test-test-validate.sh 5.0 KB runs code
- scripts/test-validate.sh 3.5 KB runs code
- scripts/test-workflow-contracts.py 67 KB runs code
- scripts/validate-asset-fidelity.py 61 KB runs code
- scripts/validate-graph-record.py 507 B runs code
- scripts/validate.sh 12 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.
- 1mo ago First seen · 6 lines scan A 38c3cd3dfa50
design-arc is a plugin published in the GitHub repository friedbeef1/design-arc (42 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
design-system-ops
Staff-level design system auditing, governance, documentation, validation, and communication — 36 skills, 4 agents, and 13 knowledge notes for the full design system lifecycle.
design-mastery
Design principles, legendary designers, and historical movements applied to UI work, with agents and workflows for brand identity, design audits, style guides, and premium landing pages.
accessibility-compliance
WCAG accessibility auditing, compliance validation, UI testing for screen readers, keyboard navigation, and inclusive design.
archetypal-alchemy
Jungian archetypes and Major Arcana symbolism turned into UI structure and color systems, with commands that generate archetype-driven components and Tailwind palettes.
humane
21 design-method skills for people and agents: evidence, prototypes, tokens, typography, semantic interactions, scroll stories, optional sound, reviews, and framework adaptation.
design-mastery
Master design through principles, legendary designers, and historical movements. Build professional brand identities with systematic workflows.