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 tomzx/agents --skill design-experimentgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/design-experiment)<a href="https://agentmods.dev/skills/tomzx/agents/design-experiment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/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/skills/tomzx/agents/design-experiment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/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 | $0.00036 | $0.00506 |
| Opus 5 | $0.00018 | $0.00253 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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 6d 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
Design Experiment
For each leap-of-faith assumption, design the test that, at minimum cost, would change your decision. The goal is decisiveness, not completeness: a test whose result cannot flip the verdict is not worth running.
Prerequisites
- Apply the shared PDLC conventions in
skills/pdlc/references/shared.md. assumptions.mdwith the ranked leap-of-faith assumptions.
Steps
- For each top assumption, define the hypothesis in testable form: If [we do X], then [we expect Y], because [belief].
- Choose the cheapest method that can falsify it:
- Fake-door / painted-door — does demand exist before building? (desirability)
- Concierge / Wizard-of-Oz — deliver the value manually; is the outcome real? (viability/feasibility)
- Prototype — can they use it / does the workflow fit? (usability)
- Survey / interview — only for beliefs you cannot observe behaviorally; treat as weak evidence.
- Set the decision threshold up front: the numeric result that means proceed vs. kill. Decide the threshold before running, not after.
- Define the audience, sample size, duration, and what you will measure. State the smallest sample that could move your confidence.
- Record what a false positive would look like (how the test could mislead you into proceeding).
- Write
experiment-plan.mdto the initiative directory.
Output Format
Use the template at skills/pdlc/templates/initiatives/experiment-plan.md. Carry the standard initiative frontmatter with phase: validate.
Outcome
If $OUTCOME_YAML is set, emit verdict: drafted.
Completion Checklist
- Hypothesis stated in if/then/because form
- Method is the cheapest that can falsify the assumption
- Decision threshold (proceed vs. kill) set before running
- Sample and duration justified
- False-positive risk acknowledged
Next Step
Load run-experiment to execute the plan and record a verdict.
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.
- 6d ago First seen · 48 lines · 36 tokens per session scan A 2ad307c1b764
design-experiment is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 506 once invoked, about $0.0002 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 2026-09-03.
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…