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 The-Pixel-Boys/shield-kya --skill kya-wrapgit clone --depth 1 https://github.com/The-Pixel-Boys/shield-kyaWrote 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/the-pixel-boys/shield-kya/kya-wrap)<a href="https://agentmods.dev/skills/the-pixel-boys/shield-kya/kya-wrap"><img src="https://agentmods.dev/badge/skills/the-pixel-boys/shield-kya/kya-wrap/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/the-pixel-boys/shield-kya/kya-wrap"><img src="https://agentmods.dev/badge/skills/the-pixel-boys/shield-kya/kya-wrap.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 | $0.00041 | $0.00391 |
| Opus 5 | $0.00020 | $0.00196 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
kya-wrap 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 12d 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.
What it actually says
Wrap a tool through Shield KYA
This plugin is a thin MCP gate. It does not decide policy. Shield KYA evaluate on the control plane is the sole PEP.
Verdicts
| Verdict | Meaning |
|---|---|
ALLOW |
Side effect may proceed |
DENY |
Do not execute. Never retry around the gate |
REQUIRE_APPROVE |
Wait for a human APPROVED. Missing approval ⇒ no irreversible effect |
Risk scores may only raise severity. They never auto-ALLOW.
Dual plane
host=ide: authoring / dry-runhost=runtime: production work
Same agent id, policy, approval, and trail on both. Label the host. Do not invent a second enforcement path in the editor.
How to wrap
- Register the agent principal (
register-agentor console). Creating an agent is itself a tool (kya.agent.register). It is not a free write. - Give the tool a stable
toolId. No marketplace adapter required. - Call evaluate (MCP
evaluate/eval-tool) before the side effect. - If
REQUIRE_APPROVE, request approval and wait. Do not execute on a pending ticket. - Offline
--offlineis a sample fixture. Do not treat it as production PEP.
Do not
- Bypass evaluate because the IDE "already reviewed" the change
- Treat scanners, ORR, or this skill as a second PEP
- Position Shield as a chargeback, dispute, or payment-recovery product
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.
- 12d ago First seen · 41 lines · 41 tokens per session scan A 2d561c0bda0b
kya-wrap is a skill published in the GitHub repository The-Pixel-Boys/shield-kya (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 391 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…