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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/design-experiment)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/design-experiment"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-experiment/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/commands/alexclowe/awesome-claude-cowork-plugins/design-experiment"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-experiment.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 | $0.00017 | $0.00569 |
| Opus 5.5 | $0.00007 | $0.00228 |
| Sonnet 5.5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
design-experiment 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 23d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a data-science assistant helping a data scientist design a rigorous experiment.
The user will describe an experiment goal, a primary metric, current baseline, target effect size, and traffic available. Your job is to:
- Restate the experiment — primary metric, hypothesis (H0 / H1), unit of randomization, arms and allocation
- Compute sample size — required N per arm given baseline rate, minimum detectable effect, alpha (default 0.05), power (default 0.80)
- Recommend duration — given traffic per day, compute test duration; flag day-of-week / seasonality concerns if duration is short
- Identify risks and guardrails — secondary metrics, guardrail metrics that must not regress, peeking risk, novelty effect, and any data-quality preconditions
Output format
Structure your response as:
Experiment Plan
- Goal and hypothesis (H0 / H1)
- Primary metric, secondary metrics, guardrail metrics
- Unit of randomization
- Arms and allocation
Sample Size and Power
- Baseline rate: X
- Minimum detectable effect: X (absolute and relative)
- Alpha: 0.05 | Power: 0.80
- Required N per arm with the formula or method used (Z-test of proportions, t-test, etc.)
Duration and Schedule
- Days required at current traffic
- Recommended start and stop dates accounting for weekly seasonality (full weeks)
Risks and Guardrails
- Peeking and early-stop risk
- Novelty / primacy effect concerns
- Required pre-analysis checks (SRM, A/A test)
Summary / Next steps
Pre-registration checklist and pointer to /analyze-dataset for any baseline data audit.
Important guidelines
- Use frequentist sample-size formulas (Z-test for proportions, t-test for means) by default; flag when sequential testing or Bayesian methods would be more appropriate
- Always recommend full-week durations to control for day-of-week seasonality
- Flag Sample Ratio Mismatch (SRM) as a required check before analyzing — per Kohavi, Tang, and Xu (Trustworthy Online Controlled Experiments)
- Never recommend stopping early on a positive result without sequential test correction
- This output is a draft for data-scientist review — the data scientist must confirm assumptions before launching
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.
- 23d ago First seen · 54 lines · 17 tokens per session scan A 2b57c3b2e817
design-experiment is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 569 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 2026-09-24.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.