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 jjanczur/tyran --skill fidelity-gategit clone --depth 1 https://github.com/jjanczur/tyranWrote 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/jjanczur/tyran/fidelity-gate)<a href="https://agentmods.dev/skills/jjanczur/tyran/fidelity-gate"><img src="https://agentmods.dev/badge/skills/jjanczur/tyran/fidelity-gate/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/jjanczur/tyran/fidelity-gate"><img src="https://agentmods.dev/badge/skills/jjanczur/tyran/fidelity-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00056 | $0.01513 |
| Opus 5 | $0.00028 | $0.00757 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
fidelity-gate 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fidelity gate — building against a frozen visual reference
Drift that goes uncaught on the first screen multiplies onto every screen after it. Measured on one initiative that skipped this: four waves of rework plus a reconciliation audit, because "looks right" had been accepted as a verdict fourteen times.
The division of labour, which is the whole idea
Appearance is read by a MACHINE. Intent is described in WORDS.
Text, typography, colour, geometry and icons are extracted from the
reference mechanically. Never let a model retype them into prose: every
restatement is a lossy copy, and the source is more precise than any
description of it — 22px/700/#0a2540 has exactly one interpretation, and
"large bold dark-blue heading" has hundreds.
Words describe only what a static reference cannot contain: which content is an example and which is binding, where the data comes from, visibility conditions, the empty state, and the states that do not render (hover, focus, error).
The overriding rule
The reference is the only source of visual truth. Handoffs, tickets and prose describe BEHAVIOUR; appearance is settled by the reference alone. When prose disagrees with the reference about how something looks, the reference wins, you decide without asking, and you record the divergence.
- An element not in the reference does not exist. Relics of older code are not carried over without an owner's decision.
- An element in the reference must be built — if necessary as an honest-empty version in the reference's own geometry.
Step 0 — the reference lives in the repo, verified
Pull it into the repo and check it is whole before trusting it: size, the file actually ends where it should, and it renders. Work only from the in-repo copy. An incomplete reference is a STOP and a report, not something to work around — half a contract silently becomes "use your judgement".
Step 1 — the inventory, before the first line of code
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.
- 9d ago First seen · 133 lines · 56 tokens per session scan A f365f434d3da
fidelity-gate is a skill published in the GitHub repository jjanczur/tyran (86 stars, last pushed 5d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,513 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 2026-08-30.
Other skills, from other repositories
ring:validating-ux-completeness
Validating that UX specifications are complete before technical design: a read-only checklist over wireframes, states, responsive behavior, accessibility, and component-library alignment, emitting a DESIGN VALIDATED / NEEDS REVISION verdict to design-validation.md. Standalone utility — run after a product-designer…
mui-styling
Material-UI (MUI) styling standards: sx-prop priority, theme tokens, spacing scale, responsive design, and accessibility. TRIGGER when: styling MUI components, defining theme tokens, or building responsive layouts. SKIP: component logic and hooks (use react-patterns); cross-stack UX/design decisions (use…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".
ds-frontend
Frontend design quality — design-system audit, token enforcement, component states, accessibility, responsive layout, theming. Use when building or reviewing UI for design consistency, a11y, or responsiveness.
craft-ux
The Craftsman standard for UI/UX — design tokens, component patterns, pixel-perfect standards, Tailwind/React implementation, motion craft, an AI-tells anti-pattern catalog, and a two-pass review protocol (static review + live browser audit). Use this whenever designing, building, reviewing, auditing, redesigning, or…
designing-responsive-experiences
Use when designing responsive experiences within ux lifecycle boundaries, especially when does the artifact make the owned decision for designing responsive experiences explicit and bounded?.