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 Rishi4792/compass --skill rk-house-stylegit clone --depth 1 https://github.com/Rishi4792/compassWrote 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/rishi4792/compass/rk-house-style)<a href="https://agentmods.dev/skills/rishi4792/compass/rk-house-style"><img src="https://agentmods.dev/badge/skills/rishi4792/compass/rk-house-style/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/rishi4792/compass/rk-house-style"><img src="https://agentmods.dev/badge/skills/rishi4792/compass/rk-house-style.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 | $0.00166 | $0.01313 |
| Opus 5 | $0.00083 | $0.00656 |
| Sonnet 5 | $0.00033 | $0.00263 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
rk-house-style 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
House Style — enforced, not advisory
The lesson this skill exists for: a prior 24 KB prose design skill already described the target look in full — and the build STILL drifted to a serif/parchment aesthetic. Prose drifts. Gates don't. This skill is the gates.
The formula: plugin CRAFT − NOVELTY + pinned tokens/components + a self-critique gate that moves the quality filter off the user.
Companion files (read before building)
SYSTEM.md ← token STRUCTURE (9 groups) + 14 component recipes + provenance
gates/rubric.md ← the craft rubric (Tier-1 MEASURABLE scripts · Tier-2 GESTALT independent scorer)
gates/anti-drift-grep.mjs ← G1: 0 off-theme colors/fonts (normalizes hex/rgb/hsl)
gates/compose-check.mjs ← G2: kit composition (first-col-left, tnum, card geometry)
seeds-to-tokens.mjs ← 4 seeds → a full coherent theme (for a NEW product)
themes/neutral-indigo.json ← the DEFAULT theme (applies everywhere)
themes/warm-fintech.json ← example generated theme
gallery/*.png ← the neutral reference gold (dashboard/form/table) the GESTALT scorer compares against
Active theme
Default = neutral-indigo for ALL projects. A product gets its OWN identity ONLY by an explicit
opt-in: choose 4 seeds (accent · neutral temperature · headline font · density/radius) →
node seeds-to-tokens.mjs '<seeds>' > themes/<product>.json → use that. Everyday work = the default.
The single design skill (no collisions)
This is the ONE design-aesthetic system Compass ships. Do NOT layer a generic "be novel / be distinctive / use a non-system font" design skill on top — that is the exact bias that causes the parchment/serif drift away from the system. Do NOT reintroduce a generic "be novel" design skill. A theme is always active (neutral-indigo is the default); identity = the theme's tokens, never overridden.
The build process — FOUR GATES, none skippable
1 · Ground (find the closest existing page). Identify the active theme + the nearest gallery pattern(s). Compose from the SYSTEM.md recipes — never invent a card/table/pill from scratch.
What ships with it
18 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.
- gallery/dashboard.html 6.6 KB
- gallery/dashboard.png 188 KB
- gallery/form.html 4.9 KB
- gallery/form.png 119 KB
- gallery/table.html 4.0 KB
- gallery/table.png 104 KB
- gates/_fixtures/clean.html 815 B
- gates/_fixtures/dirty.html 463 B
- gates/anti-drift-grep.mjs 9.1 KB runs code
- gates/compose-check.mjs 2.8 KB runs code
- gates/g3-check.mjs 3.0 KB runs code
- gates/rubric.md 4.5 KB
- seeds-to-tokens.mjs 6.6 KB runs code
- SYSTEM.md 8.2 KB
- themes/neutral-indigo.json 1.5 KB
- themes/neutral-indigo.seeds.json 150 B
- themes/warm-fintech.json 1.0 KB
- themes/warm-fintech.seeds.json 111 B
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.
- 10d ago First seen · 61 lines · 166 tokens per session scan A dcaea4aad87f
rk-house-style is a skill published in the GitHub repository Rishi4792/compass (2 stars, last pushed 5d ago), licensed MIT. It adds 166 tokens to every session and 1,313 once invoked, about $0.0008 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
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
design-standards
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card…
ln-75-architecture-diagram-builder
Creates current or target architecture diagrams as the primary deliverable. Not for UI design, architecture audits, or invented structure.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
figma-fetch
Extract frame/component structure and all visible text from a Figma design URL. Use whenever a prompt or a fetched issue contains a figma.com/design or figma.com/file link.
design
Intent-first UI design with conscious, traceable design decisions. Persists decisions in .interface-design/ for cross-session consistency. Includes domain exploration, design system generation (system.md + system.json), per-component construction with mandatory checkpoints, and craft validation tests. Modes: init…