Borrowing it
Nothing to install: this file belongs to savant0x/savant-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/savant0x/savant-code/main/.agents/skills/savant-design/SKILL.mdgit clone --depth 1 https://github.com/savant0x/savant-codeWrote 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/savant0x/savant-code/savant-design)<a href="https://agentmods.dev/skills/savant0x/savant-code/savant-design"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/savant-design/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/savant0x/savant-code/savant-design"><img src="https://agentmods.dev/badge/skills/savant0x/savant-code/savant-design.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 | $0.00054 | $0.01192 |
| Opus 5.5 | $0.00022 | $0.00477 |
| Sonnet 5.5 | $0.00011 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
savant-design 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 14d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Savant Agent Design Constitution
Scope
This constitution governs agent decisions on design tasks. It does NOT govern or modify Savant's own OpenTUI UI, theme system, or HTML export, and it never overrides ECHO Laws 1–15, separation of duties, the Perfection Loop FSM, or the engineering quality gates. State transitions, data handling, accessibility behavior, event logic, file I/O, APIs, and runtime behavior remain engineering concerns governed by ECHO and the project's own rules.
Hard gates are applicability-aware: identify the target platform (web, native, terminal, embedded, non-visual) and explain when a gate does not apply. Never turn an inapplicable web rule into a universal failure for a non-web surface.
Review Protocol (apply for every applicable design task)
- Intent. Identify the user's goal, audience, primary action or hierarchy, constraints, and applicable platform.
- Existing system. Inspect and reuse the target project's existing components, tokens, patterns, and instructions before introducing replacements. Prefer reuse over new construction (ECHO Law 7).
- Design brief. State a concise design brief and intended composition before making design changes (ECHO Law 2 — present before act).
- Hard-gate review. Check every applicable hard gate below; a failure blocks completion only when the gate is applicable and the failure is supported by evidence.
- Advisory review. Review the anti-slop advisories; treat them as recommendations unless the project-local contract makes one mandatory.
- Adversarial review. Run a review distinct from the initial generation —
re-read the changed code cold, attempt to refute each claimed PASS/FAIL,
and resolve every
file:linecitation. Adversarial findings are corrected before completion is claimed. - Correct & report. Correct failed hard gates; either correct advisories
or document a context-specific rationale for retaining them. Report changed
files, checks performed, unresolved uncertainty (
NEEDS-REVIEW), and intentionally retained advisories.
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.
- 14d ago Changed · +1 lines b397b02520c5
- 2mo ago First seen · 105 lines · 54 tokens per session scan A a5ea6970c79f
savant-design is a skill published in the GitHub repository savant0x/savant-code (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,192 once invoked, about $0.0002 per session on Opus 5.5. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.