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 jellydn/my-ai-tools --skill capability-experimentsgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/capability-experiments)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/capability-experiments"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/capability-experiments/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/jellydn/my-ai-tools/capability-experiments"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/capability-experiments.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 | $0.00021 | $0.01924 |
| Opus 5.5 | $0.00008 | $0.00770 |
| Sonnet 5.5 | $0.00004 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
capability-experiments 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 1mo 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Experiments
When to Use
Use this skill when:
- You need to present complex analysis in a readable format
- Interactive questionnaires would improve user interaction
- Exploring what's possible with next-generation model capabilities
- Multi-step reasoning is needed for architectural decisions
- You want to generate rich outputs (HTML, tables, interactive elements)
- Standard text output isn't sufficient for the task
What It Does
Teaches techniques for leveraging advanced model capabilities — HTML generation, embedded interactive elements, proactive research, and multi-step reasoning. These patterns showcase what's newly possible with next-generation models and should be used freely.
HTML Report Generation
Advanced models can generate rich, self-contained HTML. This is useful for:
Analysis Reports
Generate structured HTML reports for complex findings:
<!DOCTYPE html>
<html>
<head><style>
body { font-family: system-ui; max-width: 800px; margin: 2rem auto; }
.finding { border-left: 4px solid #e74c3c; padding: 1rem; margin: 1rem 0; }
.finding.fixed { border-color: #2ecc71; }
.severity { font-weight: 600; font-size: 0.85rem; }
</style></head>
<body>
<h1>Code Review: PR #288</h1>
<div class="finding">
<span class="severity">🔴 Critical</span>
<p>Hardcoded path in config...</p>
</div>
...
</body></html>
Use HTML reports when:
- Comparing multiple options or decisions
- Presenting structured analysis with severity levels
- Creating interactive documentation
- Showing progress or status dashboards
Embedded Questionnaires
Generate HTML questionnaires for spec interviews and quizzes:
<form id="quiz">
<div class="question">
<p>1. Why did we choose GitHub App Installation flow?</p>
<label><input type="radio" name="q1" value="a"> OAuth is deprecated</label>
<label><input type="radio" name="q1" value="b"> Org-level access ✓</label>
</div>
<button type="button" onclick="checkAnswers()">Check</button>
</form>
<script>
function checkAnswers() {
const correct = { q1: 'b', q2: 'c' };
// ... scoring logic
}
</script>
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.
- 1mo ago Changed · -2 tokens per session 368bacaff4e9
- 1mo ago First seen · 271 lines · 23 tokens per session scan A 4c3c57b267f9
capability-experiments is a skill published in the GitHub repository jellydn/my-ai-tools (124 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,924 once invoked, about $0.0001 per session on Opus 5.5. 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
ask-first
A decision guide for handling unclear requests before taking action. It uses one focused question or probe when the requested goal, context, or boundaries are not clear.
insight-miner
A manually triggered writing guide that turns notes, debugging records, design summaries, code snippets, or rough drafts into Chinese technical blog posts. It first identifies and evaluates possible article topics before writing.
book-recommender
A Chinese-language book recommendation and analysis skill that evaluates what books are about, whether they are worth reading, and how to read them.
notes-to-blog
A manually triggered guide for turning technical notes and rough material into a Chinese programming blog post. It first extracts and evaluates the main transferable idea, then writes the article after the user confirms its direction.
wisdom-decoder
A guided explanation skill for ideas from Buddhism, philosophy, and psychology. It presents a chosen topic in everyday language and connects it to practical actions, sources, and perspectives from other fields.
teach-me
A five-step teaching workflow for introducing an unfamiliar topic and guiding the learner toward applying it. It moves from an example and explanation to supported practice and an independent task.