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 addit-digital/addit-harness --skill design-conventionsgit clone --depth 1 https://github.com/addit-digital/addit-harnessWrote 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/addit-digital/addit-harness/design-conventions)<a href="https://agentmods.dev/skills/addit-digital/addit-harness/design-conventions"><img src="https://agentmods.dev/badge/skills/addit-digital/addit-harness/design-conventions/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/addit-digital/addit-harness/design-conventions"><img src="https://agentmods.dev/badge/skills/addit-digital/addit-harness/design-conventions.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 | $0.00070 | $0.01562 |
| Opus 5 | $0.00035 | $0.00781 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
design-conventions 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 8d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-conventions — generate per-project visual design conventions
Scans the current TypeScript/React project's UI layer and produces
.claude/design-conventions.md — a lightweight, project-specific visual design
convention reference. rules/typescript.md instructs loading this file first for
any UI work, so the design language loads cheaply without re-scanning each session.
Greenfield guard
This skill derives from what exists. If the project has no existing UI at all
(no Tailwind config, no token files, no components, no screens), stop and tell the
user to ask @frontend-architect first — creating a design language from a blank
slate is design work, not derivation. If only config exists (Tailwind config, a
chosen component lib, token file stubs) with no implemented screens, seed a minimal
stub from that and flag the rest for the architect.
When to run
- First time in a project with existing UI — before any substantial UI work.
--refresh— when the design system has evolved or a new visual pattern has been established. Merges new patterns into the existing file; preserves hand-edits.- Prompted by a gap — if you hit a pattern the file doesn't cover while coding, append the rule inline (don't re-run the full scan).
Procedure
1. Confirm context
Verify you're in a TS/React project: check for package.json, a tsconfig.json,
and the presence of .ts/.tsx files. If absent, stop and say so.
Check whether .claude/design-conventions.md already exists. If it does and
--refresh was not passed, report what's there and ask the user to pass --refresh
to merge new patterns.
2. Scan the project's UI layer
Read these artifacts in priority order:
a. Design token / config foundation
tailwind.config.{ts,js}— custom color palette, spacing scale, type scale, breakpoints, font families, border-radius tokens, shadow scaletokens/ordesign-tokens/directory — primitive and semantic token definitions- CSS custom-property files (
variables.css,globals.css,:rootblocks) theme.{ts,js}ortheme/— if using a component lib (MUI, Chakra, Mantine)
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.
- 8d ago First seen · 139 lines · 70 tokens per session scan A 3beffc2cf433
design-conventions is a skill published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 1,562 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 2026-08-31.
Other skills, from other repositories
memstack-security-csp-headers
Use this skill when the user says 'CSP', 'Content-Security-Policy', 'security headers', 'HSTS', 'X-Frame-Options', 'clickjacking', 'unsafe-inline', 'unsafe-eval', or needs to audit, generate, or fix HTTP security headers for a web application. Do NOT use for API route audits or dependency scanning.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
ijfw-ui-spec
Use when the user says: 'ui spec', 'design contract', 'ui audit setup', 'lock the design', 'visual contract', 'ui review setup', or '/ijfw-ui-spec'. Produces UI-SPEC.md as the visual design contract before any frontend or visual-artifact build, and dispatches ijfw-ui-auditor as the final 6-pillar gate.
ui-animation
Builds, reviews, and measures UI motion, including springs, gestures, scroll effects, and curve fitting from recordings. Use when asked to "add animation", "match this easing", "reverse engineer this motion", or find animation opportunities. For action semantics use product-design; for visual layout use ui-design.
ui-design
Designs and builds React/Next/Tailwind UI and audits visual and interaction defects. Use when asked to "build a landing page", "extract our design system", "add dark mode", "make this responsive", "remove UI slop", or "audit this component". For product decisions use product-design; for browser measurements use…
typography-audit
Audits font loading, type scales, measure, spacing, OpenType, and rendered punctuation with 78 scoped rules. Use when asked to "audit typography", "fix the fonts", or "review my type system". For a new visual direction use ui-design Direction; for general UI defects use ui-design Audit.