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 itseffi/agentic-os --skill experiment-designgit clone --depth 1 https://github.com/itseffi/agentic-osWrote 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/itseffi/agentic-os/experiment-design)<a href="https://agentmods.dev/skills/itseffi/agentic-os/experiment-design"><img src="https://agentmods.dev/badge/skills/itseffi/agentic-os/experiment-design/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/itseffi/agentic-os/experiment-design"><img src="https://agentmods.dev/badge/skills/itseffi/agentic-os/experiment-design.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 | $0.00021 | $0.00342 |
| Opus 5.5 | $0.00008 | $0.00137 |
| Sonnet 5.5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
experiment-design 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.
What it actually says
Experiment Design
Design robust experiments to test product hypotheses.
When to Use
When you have a hypothesis and need to design an experiment to validate it.
The Process
1. Factor Breakdown
Analyze your goal and system:
- What factors could influence the outcome?
- Which are controllable vs. environmental?
- What are the key variables?
2. Experiment Structure
For each factor, define:
- Hypothesis: What you expect to happen
- Independent variable: What you're changing
- Dependent variable: What you're measuring
- Control group: Baseline comparison
- Experimental group: Who gets the change
- Measurement method: How you'll collect data
- Confounding variables: What else could affect results
3. Sample Design
- Who participates?
- How many needed for statistical significance?
- How will you recruit/select?
4. Timeline
- How long to run?
- When to check results?
- What's the minimum detectable effect?
5. Stop/Scale Rules
- What results mean "stop"?
- What results mean "scale"?
- What's inconclusive?
Output Format
For each experiment:
- Hypothesis statement
- Variables (independent, dependent)
- Groups (control, experimental)
- Sample size and selection
- Measurement approach
- Success criteria
- Stop/scale rules
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
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.
- 1mo ago First seen · 63 lines · 21 tokens per session scan A 243b2089b944
experiment-design is a skill published in the GitHub repository itseffi/agentic-os (117 stars, last pushed 14d ago), licensed MIT. It adds 21 tokens to every session and 342 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
vague-requirement-unpacker
A planning aid for turning a vague business request into questions, a narrowed scenario, and an initial scope outline. It is meant for early alignment before a full PRD, or product requirements document, exists.
reviewcourt
A review tool for completed Tencent Meeting requirements or technical-plan meetings. It turns the meeting notes and transcript into a verdict, such as approved, conditionally approved, rejected, or lacking enough information.
competitive-product-research
A research workflow for comparing products and explaining how they differ. It examines user experience and business strategy, then produces a report in HTML or Markdown with traceable sources.
opc-board
A review skill for testing whether a one-person business, side project, or open-source idea is practical. Five advisers score its logic, ability to be delivered, growth potential, viability, and risks, then give a Go or No-Go result.
pm-requirement-review-simulator
A rehearsal for reviewing a product requirements document, or PRD—a written description of what a product or feature should do. Five cross-functional roles challenge the requirements before the real meeting.
ide-briefing-ppt
Generates a single-file 1280x720 HTML presentation by reusing the frozen Light IDE visual system extracted from LLM Wiki 分享.html. Use only when the user names ide-briefing-ppt, asks to reuse that deck's UI, or explicitly requests the combined light-gray canvas, white panels, amber accent, terminal, and file-tree…