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 run-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/run-experiment)<a href="https://agentmods.dev/skills/tomzx/agents/run-experiment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/run-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/run-experiment"><img src="https://agentmods.dev/badge/skills/tomzx/agents/run-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 | $0.00033 | $0.00535 |
| Opus 5 | $0.00016 | $0.00267 |
| Sonnet 5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
run-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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Experiment
Executes the experiment-plan.md, collects the data, and records a verdict against the threshold that was set before the test. This is where the PDLC earns its keep: a negative result here is a successful kill, not a failure.
Prerequisites
- Apply the shared PDLC conventions in
skills/pdlc/references/shared.md. experiment-plan.mdwith a pre-set decision threshold.
Steps
- Run the test per the plan: stand up the fake-door, run the concierge flow, deploy the prototype, or field the survey.
- Collect the raw data and observations. Keep both quantitative results and qualitative surprises.
- Compare the result to the pre-set threshold. State the verdict explicitly:
proceed,kill, orinconclusive. - If
inconclusive, diagnose why (sample too small, test not decisive, threshold wrong) and decide whether to re-run with a better test or proceed under reduced confidence (recorded as an assumption). - Capture learnings: what surprised you, what you now believe that you didn't before.
- Watch for false positives: would you have seen this result even if the assumption were false?
- Write
experiment-result.mdto the initiative directory.
Output Format
Use the template at skills/pdlc/templates/initiatives/experiment-result.md. Carry the standard initiative frontmatter with phase: validate.
Outcome
If $OUTCOME_YAML is set:
| Verdict | When |
|---|---|
proceed |
Result met or exceeded the threshold |
kill |
Result missed the threshold; the assumption is false |
inconclusive |
Test could not reach the threshold; re-run or proceed-with-caution |
Completion Checklist
- Result compared to the pre-set threshold, not a post-hoc rationalization
- Verdict stated explicitly (proceed / kill / inconclusive)
- False-positive risk considered
- Surprises captured as learnings
Next Step
Run the Validate gate via make-decision. On proceed, load define-vision to begin Strategy. On kill, the orchestrator runs kill-initiative. On pivot, return to design-experiment with a revised test.
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 · 50 lines · 33 tokens per session scan A b4d6876b1531
run-experiment is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 535 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…