experiment-program-management

experiment-program-management is a skill for Claude Code, Codex from krillinai/growth-skills. It costs 72 tokens per session (2,894 once invoked), scanned A, original, MIT.

Workflows for managing an experimentation program, meaning a coordinated set of tests used to reduce uncertainty and guide decisions.

In plain words
What is it for?
Use it to audit or design experiment intake, prioritization, traffic allocation, quality checks, incident handling, readouts, and long-term validation.
Why use it?
It helps teams choose which tests matter, share limited traffic and capacity, handle conflicting tests, and keep inconclusive results and follow-up visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit or design experiment intake, prioritization, traffic allocation, quality checks, incident handling, readouts, and long-term validation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/krillinai/growth-skills/experiment-program-management
Install

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.

Any agent
npx skills add krillinai/growth-skills --skill experiment-program-management
Clone the repo
git clone --depth 1 https://github.com/krillinai/growth-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for experiment-program-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/krillinai/growth-skills/experiment-program-management/github.svg)](https://agentmods.dev/skills/krillinai/growth-skills/experiment-program-management)
Your own site
<a href="https://agentmods.dev/skills/krillinai/growth-skills/experiment-program-management"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/experiment-program-management/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.

agentmods 80×15 button for experiment-program-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/krillinai/growth-skills/experiment-program-management"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/experiment-program-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.02894
Opus 5 $0.00036 $0.01447
Sonnet 5 $0.00014 $0.00579
Haiku 4.5 $0.00007 $0.00289

Measured 11d ago against content hash d098a7d19789, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

experiment-program-management 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 11d 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.

skills/growth-operations/references/modules/experiment-program-management/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Program Management

Turn many experiments and alternative evidence designs into a trustworthy decision system. Govern which uncertainties enter, how scarce traffic and capacity are allocated, where concurrent interventions collide, when evidence is ready, how incidents and inconclusive results remain visible, and whether learning changes later decisions. Experiment volume and win rate are activities, not program outcomes.

Read program-contract.md before accepting program scope, experiment inventory, states, owners, systems, periods, evidence, or health claims. Read portfolio-intake-and-prioritization.md before accepting ideas, classifying work, comparing decision value, or allocating traffic and capacity. Read traffic-quality-and-evidence-operations.md before defining concurrency, preflight gates, incidents, maturity, readouts, follow-through, or long-term checks. Read learning-governance-market-and-actions.md before governing reuse, program health, decision rights, market transfer, personal data, or external actions. Read output-contract.md before delivery. Use playbook-sources.md for the pinned Growth Playbook basis.

Select One Mode

Mode Use
audit Inspect a current experimentation program for selection, contract, quality, traffic, capacity, interference, maturity, learning, follow-through, or governance failures
design Build an evidence-bounded program contract, portfolio, operating gates, cadence, repository, and health system
refresh Version the program after strategy, traffic, capacity, evidence maturity, incidents, proxy validity, long-term outcomes, platform, or governance changes

Name one primary mode and state draft, reconciling, decision-ready, approved-record, active-record, superseded, or expired. A record state does not prove approval, assignment, exposure, completion, adoption, or impact.

Read the full file on GitHub · 109 lines

Files

What ships with it

6 files 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.

Changes

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.

  1. 11d ago First seen · 109 lines · 72 tokens per session scan A d098a7d19789

Subscribe to this mod's changes

experiment-program-management is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 14d ago), licensed MIT. It adds 72 tokens to every session and 2,894 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories