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 cyyeh/skills-playground --skill system-findergit clone --depth 1 https://github.com/cyyeh/skills-playgroundWrote 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/cyyeh/skills-playground/system-finder)<a href="https://agentmods.dev/skills/cyyeh/skills-playground/system-finder"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-finder/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/cyyeh/skills-playground/system-finder"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-finder.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 | $0.00134 | $0.02136 |
| Opus 5 | $0.00067 | $0.01068 |
| Sonnet 5 | $0.00027 | $0.00427 |
| Haiku 4.5 | $0.00013 | $0.00214 |
Grade A, and why
system-finder 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 11d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Finder
Discover software systems that match a user's target and present a structured comparison for selection. The target can be a specific system name ("Kafka"), a software category ("message queues"), or a functional requirement ("I need real-time data processing"). The output is a comparison table written to a user-chosen output directory (default: dist/[system-name]/finder-report.md).
First-Run Welcome
When triggered without a specific query, introduce the skill:
I can help you find and compare software systems.
Tell me what you're looking for:
- A specific system -- "Tell me about Kafka" or "What is CockroachDB?"
- A category -- "What message queues exist?" or "Compare CI/CD tools"
- A requirement -- "I need real-time analytics" or "I need a database for time series data"
- Alternatives -- "What are alternatives to Redis?" or "Kafka vs RabbitMQ"
I'll research options, compare them, and help you pick the right one.
Output Directory
Always ask the user where to save the finder report before writing any files. Use AskUserQuestion to prompt:
Where would you like me to save the finder report? Default:
dist/[system-name]/
Accept the user's chosen path. If they accept the default or say something like "that's fine" or "default", use dist/[system-name]/. Store this path as [output-dir].
Exception: When called by the system-explorer orchestrator with a pre-determined output directory, use that directory without re-asking.
Create the directory if it does not exist.
The Process (3 Phases)
Phase 1: Understand the Target
Parse the user's query to determine the type:
- Specific system -- The user named a system ("Kafka", "Redis", "Terraform"). Confirm the target: "You want to explore Apache Kafka?" Then suggest proceeding directly to system-analyzer. Skip Phase 2 unless the user wants to see alternatives.
- Category -- The user named a software category ("message queues", "databases", "CI/CD tools"). Proceed to Phase 2 to discover systems in that category.
- Requirement -- The user described a need ("I need real-time data processing", "something for container orchestration"). Map the requirement to one or more categories, then proceed to Phase 2.
- Comparison -- The user wants to compare specific systems ("Kafka vs RabbitMQ"). Proceed to Phase 3 with those systems pre-selected.
What ships with it
1 file 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.
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.
- 11d ago First seen · 175 lines · 134 tokens per session scan A 04b6ccdd0e74
system-finder is a skill published in the GitHub repository cyyeh/skills-playground (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 134 tokens to every session and 2,136 once invoked, about $0.0007 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…