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 agentmods add skills/bitjaru/styleseed/ss-dialnpx skills add bitjaru/styleseed --skill ss-dialgit clone --depth 1 https://github.com/bitjaru/styleseedWrote 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/bitjaru/styleseed/ss-dial)<a href="https://agentmods.dev/skills/bitjaru/styleseed/ss-dial"><img src="https://agentmods.dev/badge/skills/bitjaru/styleseed/ss-dial.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.02765 |
| Opus 5 | $0.00057 | $0.01383 |
| Sonnet 5 | $0.00023 | $0.00553 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
ss-dial 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 4d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dial an axis
Registry-first artifact boundary
When .styleseed/project.json and .styleseed/artifacts/index.json exist, resolve the requested artifact ID first, then read only .styleseed/bundles/<artifact-id>.md and .styleseed/manifests/<artifact-id>.json. Never fall back to the global legacy bundle for a registry project. Legacy projects may use .styleseed/effective-rules.md only when no registry exists.
"Make it more minimal" is something you can just say — the model already reads plain
language. A skill only earns its place where one word must move many tokens at once, in a
coordinated way, without breaking a rule — and where doing it by hand gives an inconsistent
result (some tokens changed, the grid broken, a second accent introduced). That's what
/ss-dial is: not interpretation, but a deterministic ramp + guardrails + re-gate.
If the request is a mood word ("more premium", "more editorial", "more playful"), that's not
one axis — it's a combination of positions across several axes. Use /ss-restyle <preset> for those. /ss-dial moves exactly one axis.
When NOT to use
- A vague vibe the model can just apply from words ("cleaner", "nicer") → don't wrap it in a skill; say it.
- A named aesthetic (Swiss / editorial / brutalist) →
/ss-restyle(a preset of dial positions). - Changing the accent hue itself (rebrand) → edit the lock's Key color directly, then re-derive.
- No
STYLESEED.mdlock yet → run/ss-buildor/ss-setupfirst; there's nothing to dial from.
The mechanic (every axis)
- Read
STYLESEED.md— find the axis's current position (Mood/Density/Radius/Elevation/ Type scale/Font weight/Motion fields). If the lock doesn't record it, infer it from the code. - Move ONE position in the requested direction on that axis's ramp (below). "more X" = one
step; an explicit target ("density: dense") jumps straight there. Clamp at the ends — you
cannot dial past
denseor belowairy. If already at the end, say so and stop (this is why "each use makes it more" is bounded, not runaway). - Apply the whole coordinated token set for the new position across every file that uses those tokens — not just the one component in view. This is the point: system-wide, consistent.
- Respect the guardrails (each axis lists its own). Never break a Golden Rule to satisfy a dial — if "denser" would push a touch control below 44px, stop at the floor and note it.
- Update
STYLESEED.mdwith the new position (so it persists and the next prompt obeys it). - Re-run the Quality Gate (
/ss-score, loop to ≥ 80). A dial that drops the score below 80 is reverted or fixed, not shipped. Report: axis, old → new position, score.
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.
- 4d ago First seen · 175 lines · 114 tokens per session scan A cb2961f041fc
ss-dial is a skill published in the GitHub repository bitjaru/styleseed (939 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,765 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
sigil-migration
Before migrating, audit the existing project.
sigil-component
Every Sigil component lives in packages/components/src/ and follows this pattern.
design-to-code
Lanhu to Code workflow for Claude Code. Convert Lanhu design URLs into Vue/React frontend code with component reuse, design token mapping, TODO-safe business logic, and optional code review.
brand-motion-guidelines
This skill should be used when the user asks to "write motion guidelines", "create a brand motion system", "define easing and timing tokens", "document our animation principles", "build a motion language like Slack/IBM/Klarna", "set up entrance/exit/transition rules", or "add a reduced-motion / accessibility section".…
material-ui-styling
Chooses the right Material UI styling approach (sx, styled, theme overrides, global CSS) from official MUI guidance. Use when styling @mui/material components, customizing themes, overriding slots, or comparing sx vs styled.
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.