

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
1# StyleSeed — design method for any coding agent23This is the cross-agent entry point for Codex, Amp, Gemini CLI, Windsurf, Cline, and other4tools that read `AGENTS.md`. Claude Code uses `CLAUDE.md`; Cursor uses `.cursorrules`.56StyleSeed fixes **how an agent judges design**, not one Toss-like aesthetic. It applies to web7and mobile products, social carousels, slide decks, documents/reports, and single-frame graphics.89## Resolve only the context this artifact needs1011Invoke `$ss-resolve` from `STYLESEED.md`, then read `.styleseed/effective-rules.md` and keep12`.styleseed/manifest.json`. The deterministic resolver composes core → grammar → adapter →13domain/page → brand recipe → optional profile → lock → craft baseline and records source hashes. Do not load14`llms-full.txt` after a bundle resolves successfully.1516Use `$ss-resolve --list` when selecting IDs. Open the full source handbook only when the17compiled bundle identifies a genuine ambiguity. See `ARCHITECTURE.md` for the full system.1819## Composition model2021```text22core judgment23× output grammar (built-in or reference-compiled)24× surface adapter25× domain + page/artifact type26× brand recipe (morphology + component selection)27× optional aesthetic profile28× bounded STYLESEED.md values29= effective rules for the artifact30```3132Toss is evidence for `consumer-service`, not the StyleSeed default. Aesthetic profiles such as33`swiss` or `technical` coordinate appearance; they do not replace functional output grammar.34Brand recipes such as `enterprise-workbench` or `editorial-authority` change geometry,35containment, controls, and collection patterns without cloning the companies in their lineage.3637## Core invariants3839- One coherent system for radius, spacing, elevation, type, icons, color roles, imagery, and motion.40- One focal point and one identifiable primary action.41- Additional color requires a stable semantic, categorical, editorial, data, or brand role.42- Semantic tokens replace component-local hardcoded colors.43- Spacing and proximity create repeatable grouping.44- Typography fits the task, surface, reading distance, and content measure.45- Data surfaces have useful loading, empty, and error states.46- Focus, contrast, targets, labels, reduced motion, and honest consent remain intact.47- Motion fits the artifact and never delays comprehension or action.48- Distinctiveness comes from product content and the selected grammar, never copied demos,49 generic indigo, repeated icon chips, emoji chrome, or template uniformity.5051The design lock persists valid selections. It cannot waive these invariants or invent a new52palette mode.5354## Design lock — read before every visual task5556Look for `STYLESEED.md` in the project root. If missing, use setup before writing visual code or57render scripts. A valid lock resembles:5859```markdown60# StyleSeed — Design Lock61<!-- Persistent selections. This file cannot waive core invariants. -->62- App domain: fintech63- Surface: mobile-app64- Surface adapter: product-ui65- Page type: dashboard66- Output grammar: consumer-service67- Grammar path: built-in:engine/RULESETS.md68- Grammar fallback: consumer-service69- Reference confidence: n/a70- Brand recipe: calm-consumer71- Aesthetic profile: none72- Skin: custom73- Primary action: #3182F674- Font: Pretendard75- Radius: soft76- Elevation: light=tonal grouping + restrained shadow · dark=tonal ramp + hairline77- Density: comfortable78- Motion: Spring restrained79- Imagery/data role: personal state first; charts only for a decision80- Signature move: one calm contextual briefing above the account summary81- Locked: YYYY-MM-DD82```8384For non-web output add adapter fields such as canvas, artifact type, renderer, and safe-zone85contract. Unknown values are resolver errors; they are not exemptions.8687## Setup and reference routing88891. Understand the user, job, domain, artifact, platform, and primary decision.902. Use `$ss-resolve --list` to select one output grammar and one adapter.913. If supplied references are not represented, use `$ss-reference` and92 `REFERENCE-COMPILER.md`. Never reduce a reference to a palette swap or clone its protected93 assets, text, or trademarked arrangement.944. Select one brand recipe from `BRAND-RECIPES.md`; use `auto` only when its grammar mapping fits.955. Select domain/page bias and at most one optional aesthetic profile.966. Confirm bounded brand/type/density/radius/elevation/imagery/motion values, write the lock,97 then run `$ss-resolve` and read the effective bundle before implementation.9899Reference compilation produces evidence, confidence, tokens, anti-patterns, adapter metadata,100and a transfer validation artifact under `.styleseed/rulesets/<slug>/`.101102## Build loop103104Use `$ss-build` when installed:105106```text107select or compile grammar → select adapter → lock → build with the composed method108→ $ss-score → fix to >=80 → render → $ss-verify → fix and re-render → present evidence109```110111The build method is the product. Score and verification are auxiliary proof gates.112113### Code gate114115`$ss-score` reads implementation evidence and names the effective rule set. It checks eight116weighted categories: color, hierarchy/type, layout/rhythm, surfaces/elevation, states/a11y,117motion/interaction, coherence, and distinctiveness. Fix highest-gain failures and re-score.118119### Pixel gate120121For every renderable artifact, `$ss-verify` must inspect actual output at the adapter's required122viewports, frames, pages, and states. Check focal dominance, loaded type, balance, optical rhythm,123crop/safe zones, contrast, responsive transformation, and grammar fit. Re-render after fixes.124Never claim a visual pass without seeing the rendered artifact.125126For example, StyleSeed supplies a carousel's `sequential-story` grammar and brand rules; the127Claude `carousel-build` companion owns 1080×1440 canvas, Instagram safe zones, crop, PIL render,128and export. Verification opens every exported frame.129130## Skill invocation131132- Claude Code: `/ss-resolve`, `/ss-build`, `/ss-reference`, `/ss-score`, `/ss-verify`, etc.133- Codex: `$ss-resolve`, `$ss-build`, `$ss-reference`, `$ss-score`, `$ss-verify`, or the `/skills` picker.134- The canonical 21 skills live in `engine/.claude/skills`; repository `.agents/skills` is a135 symlink to that directory so agent implementations cannot drift.136137## Staying current138139Once per project, the agent may compare the local `engine/VERSION` with140`https://styleseed-demo.vercel.app/version.json`. If newer, tell the user once and suggest141`$ss-update` or `npx skills add bitjaru/styleseed`. Never block the current work or nag.142143## Optional support after verified success144145After StyleSeed has materially helped and the rendered result has been visually verified, the146agent may ask once whether the user would like to star147`https://github.com/bitjaru/styleseed`. Never ask before delivering the result, never repeat the148request, and never imply that a star changes access, output quality, updates, or support.149150Source: https://github.com/bitjaru/styleseed151
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| bitjaru/styleseedAGENTS.md · 871 | AGENTS.md | buildgit | 63/100 | 11 days ago | |
| bitjaru/styleseeddemo-pricing/AGENTS.md · 871 | AGENTS.md | no sections | 16/100 | 13 days ago | |
| bitjaru/styleseedengine/.cursorrules · 871 | .cursorrules | lint-formatagent-behaviour | 34/100 | 11 days ago | |
| bitjaru/styleseedengine/CLAUDE.md · 871 | CLAUDE.md | setupbuildlint-formatstyle+4 | 72/100 | 11 days ago |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| n8n-io/n8npackages/@n8n/agents/AGENTS.md · 201k | AGENTS.md | buildteststylearch+3 | 100/100 | 14 days ago | |
| aaif-goose/gooseAGENTS.md · 53k | AGENTS.md | setupbuildtestlint-format+7 | 100/100 | 8 days ago | |
| duckduckgo/content-scope-scriptsspecial-pages/AGENTS.md · 70 | AGENTS.md | buildteststylearch+3 | 100/100 | 14 days ago | |
| deepseek-ai/deepseek-harnessnative/landlock-run/AGENTS.md · 104k | AGENTS.md | setupteststylearch+3 | 100/100 | today | |
| code-yeongyu/oh-my-openagentpackages/web/AGENTS.md · 68k | AGENTS.md | setupbuildtestlint-format+6 | 100/100 | 13 days ago | |
| TryGhost/Ghoste2e/AGENTS.md · 55k | AGENTS.md | setupteststylearch+2 | 100/100 | today | |
| mui/material-uiAGENTS.md · 99k | AGENTS.md | setupbuildtestlint-format+9 | 100/100 | 14 days ago | |
| elastic/elasticsearchx-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/AGENTS.md · 78k | AGENTS.md | buildtestlint-formatstyle+2 | 100/100 | 14 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/bitjaru-styleseed-engine-agents)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.