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 KxSystems/kx-skills --skill kx-breadcrumbsgit clone --depth 1 https://github.com/KxSystems/kx-skillsWrote 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/kxsystems/kx-skills/kx-breadcrumbs)<a href="https://agentmods.dev/skills/kxsystems/kx-skills/kx-breadcrumbs"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kx-breadcrumbs/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/kxsystems/kx-skills/kx-breadcrumbs"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kx-breadcrumbs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.03061 |
| Opus 5 | $0.00024 | $0.01530 |
| Sonnet 5 | $0.00010 | $0.00612 |
| Haiku 4.5 | $0.00005 | $0.00306 |
Grade A, and why
kx-breadcrumbs 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KX Dashboards — Breadcrumbs Component
Dependency: requires
kx-dashboard-core. Load it first — it owns the dashboard envelope, screen, widget wrapper, ViewState entry structure, binding patterns, UUID rules, and the deploy paths. This skill only specifies the Breadcrumbsoptionsblock and its ViewState wiring.Precedence: where this skill and any other skill disagree about the Breadcrumbs component, this skill wins.
Notation Legend — read before emitting anything
The options object below is presented as one annotated shape per top-level section. Every documented key appears exactly once, inline in its section, as a slot. There is no separate skeleton and no separate key-reference list — the annotation is the reference.
Each slot is one of two kinds:
◆Rule-Driven Slot (RDS). The◆symbol marks a value that this skill's documented rule (or an explicit user instruction) determines. Absent a documented reason or user instruction, emit the baseline value shown in the sample JSON, recorded in the slot's inline annotation. Each RDS is annotated inline with: its UI label, type, allowed values, a one-line rule/description summary, its baseline, and any Default Override.- VERBATIM-LOCK constant (printed literally, no
◆). Emit the exact value shown — every number, string (including""), boolean, and nested object — unchanged. The sample is not a license to substitute a "similar", "reasonable", "rounded", or "tidied" value.
Classification rule: a key is an RDS if and only if it has a documented rule in this skill. Every other key — and every key inside an otherwise-undocumented nested block (Alignment, format, Basic.DataSourceMapping) — is verbatim-lock.
ViewState-ref objects. Inside any { "_dashboardsType": "viewstate", "value": ... } object, "_dashboardsType" is always verbatim-lock and only "value" is an RDS.
The annotated shapes use
//comments and the◆symbol for documentation only. Emitted KX JSON contains no comments and no◆— replace each◆with the resolved value (baseline unless a rule/user changes it).
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 · 239 lines · 48 tokens per session scan A 21ba7a49443c
kx-breadcrumbs is a skill published in the GitHub repository KxSystems/kx-skills (16 stars, last pushed 8d ago), licensed Apache-2.0. It adds 48 tokens to every session and 3,061 once invoked, about $0.0002 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
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…