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 harness/harness-skills --skill create-experimentgit clone --depth 1 https://github.com/harness/harness-skillsWrote 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/harness/harness-skills/create-experiment)<a href="https://agentmods.dev/skills/harness/harness-skills/create-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/create-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/harness/harness-skills/create-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/create-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 | $0.00140 | $0.00941 |
| Opus 5.5 | $0.00056 | $0.00376 |
| Sonnet 5.5 | $0.00028 | $0.00188 |
| Haiku 4.5 | $0.00014 | $0.00094 |
Grade A, and why
create-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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Experiment
Compatibility entrypoint kept for direct /create-experiment invocation. This
skill does not duplicate any workflow - it hands the entire creation flow to
manage-experiments's Create experiment
section and returns once that flow completes.
Tools
Performs no operations of its own; it uses the operations of manage-experiments' Create experiment flow, named in tool-map.md.
Instructions
Step 1: Delegate
Read manage-experiments/SKILL.md and follow
its Phase 1: Establish scope and Create experiment section (Steps 1-8)
exactly as written, using the current request's scope (org/project), parent
flag + environment, hypothesis, metrics, treatments, window
(startAt/endAt), and rule. Do not re-derive or re-interpret any of that
section's logic here - this skill has no independent instructions for
resolving treatments, choosing metrics, or drafting the payload; it only
exists so /create-experiment remains a valid invocation.
If the tool interface you're running under can't follow a markdown link to
load another skill's file on demand, read
skills/fme/manage-experiments/SKILL.md directly (same repo, relative path) and
proceed the same way.
Step 2: Return the result
Once manage-experiments' Step 8 (Verify) completes, report the created
experiment's id, status, and the verified fields (baseline/comparison
treatments, key/supporting metrics, rule) back to the user. Don't add a
second verification pass - manage-experiments' Step 8 is authoritative.
Examples
- "Create an experiment on the new-checkout flag" → delegate to manage-experiments Create flow, return created id
- "Set up an A/B test for the pricing page" → same delegation
- "Pause experiment pricing_test_2" → not this skill; route to manage-experiments (Update)
- "Did the checkout experiment win?" → not this skill; route to review-experiment-results
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.
- yesterday Changed · +6 lines 46eca634ff98
- 9d ago First seen · 78 lines · 140 tokens per session scan A bab34816a060
create-experiment is a skill published in the GitHub repository harness/harness-skills (117 stars, last pushed yesterday), licensed Apache-2.0. It adds 140 tokens to every session and 941 once invoked, about $0.0006 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 2026-10-07.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".