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-explorergit 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-explorer)<a href="https://agentmods.dev/skills/cyyeh/skills-playground/system-explorer"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-explorer/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-explorer"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-explorer.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 | $0.00130 | $0.01748 |
| Opus 5 | $0.00065 | $0.00874 |
| Sonnet 5 | $0.00026 | $0.00350 |
| Haiku 4.5 | $0.00013 | $0.00175 |
Grade A, and why
system-explorer 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Explorer
Single entry point that orchestrates three sub-skills into a complete learning pipeline: discover systems, analyze in depth, and generate an interactive course -- with user checkpoints between each phase.
First-Run Welcome
When triggered, greet the user and explain the pipeline:
I can help you explore and learn any software system -- from discovery to a full interactive course.
Here's how it works:
- Discover -- Find and compare systems that match what you're looking for
- Analyze -- Deep-dive research with layered depth (beginner to advanced)
- Generate -- Build an interactive multi-page HTML course you can browse
Just tell me what you want to explore:
- A specific system -- "Explore Kafka"
- A category -- "I want to understand message queues"
- A requirement -- "Help me find a database for time-series data"
Flow
User query
|
v
+---------------------+
| 1. Clarify target | Ask questions if ambiguous
+----------+----------+
v
+---------------------+
| 2. Ask output dir | User chooses where artifacts go
+----------+----------+
v
+---------------------+
| 3. system-finder | Discover & compare systems
| -> comparison | User picks system(s)
+----------+----------+
v Checkpoint
+---------------------+
| 4. system-analyzer | Deep-dive research
| -> analysis files| User reviews findings
+----------+----------+
v Checkpoint
+---------------------+
| 5. system-to-course | Generate HTML site
| -> [output-dir] | User reviews output
+----------+----------+
v
Done
Smart Shortcuts
Skip phases when they are not needed:
- Specific system named ("explore Kafka") -- Skip finder and go directly to analyzer. Confirm with user: "You want to explore Apache Kafka. Shall I start the deep-dive analysis, or would you prefer to see alternatives first?"
- Existing finder-report.md -- If
[output-dir]/finder-report.mdexists, offer to skip finder: "I found an existing finder report. Want to use it, or start fresh?" - Existing analysis -- If
[output-dir]/analysis.jsonor[output-dir]/analysis.mdexists, offer to skip to course generation: "There's already an analysis on file. Jump to course generation, or redo the analysis?" - Multiple systems -- If the user wants to compare multiple systems, run analyzer for each (potentially in parallel using the Agent tool), then generate a combined or separate course site per system.
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.
- 9d ago First seen · 154 lines · 130 tokens per session scan A 837c84fd092f
system-explorer is a skill published in the GitHub repository cyyeh/skills-playground (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 1,748 once invoked, about $0.0006 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.