Home / jnpiyush / agentx · .github/skills/development/experimentation-loop/SKILL.md · GitHub

experimentation-loop skillA

experimentation-loop is agent-read markdown (skill) from jnpiyush/agentx: Run a metric-driven autonomous experimentation loop on an isolated branch. Use when a task has a measurable target (latency, bundle size, test pass-rate, build time, memory, score, accuracy) and the agent should propose changes, measure each attempt against a baseline, keep wins and revert losses, and produce a durable audit trail. Distinct from iterative-loop, which is correctness-driven..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Experimentation Loop

> **Purpose**: Drive a measurable metric in a chosen direction by running many small, isolated experiments, keeping wins, and reverting losses.
> **Scope**: Branch isolation, metric definition, attempt audit trail, keep/revert decision rule.

---

## When to Use This Skill

- A target metric exists and can be measured by a deterministic command
- The desired direction is known (lower latency, higher pass-rate, smaller bundle)
- Many small attempts are likely needed
- Reverting a bad attempt is cheap (single git checkout)
- A durable record of every attempt is valuable

## When NOT to Use

- Correctness work where the goal is binary "tests pass" -- use `iterative-loop`
- Tasks without a measurable metric or a way to compute it from a single command
- Risk-bearing changes that should not auto-revert (use a normal review flow)
- Production hotfixes (use targeted change with explicit review)

## Prerequisites

- Clean working tree on a non-main branch
- A metric command that exits 0 and prints a single numeric value, OR a JSON value reachable by a fixed JSON pointer
- A baseline measurement captured before the loop starts
…

Read the whole file at its exact version.

How to install

Latest version
mdr add jnpiyush/agentx/experimentation-loop@v1.1.0
Exact content
mdr add jnpiyush/agentx/experimentation-loop@sha256:14a05da1300d7bd2

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_67h3kvtnbd32pbr6.svg)](https://markdownregistry.com/a/art_67h3kvtnbd32pbr6)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.1.0 latest2026-09-15 f17c505 14,339 BA view · diff
v1.1.02026-05-22 c9b598a 14,337 BA view · diff
v1.0.02026-04-29 1c1ff57 9,172 BA view · diff
v1.0.02026-04-28 21e2bfe 8,129 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14339 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_67h3kvtnbd32pbr6
GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/experimentation-loop
GET https://markdownregistry.com/api/v1/blob/14a05da1300d7bd2baa16deb2e3ebeb3ac80856c53e579fb8c59af11068089d7

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from jnpiyush/agentx

000-frontier-core rules
jnpiyush/agentx · .cursor/rules/000-frontier-core.mdc · Frontier core operating contract for Cursor. Always applied.
git:20260915.f17c505 · audit A · 16 stars
ai rules
jnpiyush/agentx · .cursor/rules/ai.mdc · AI / agent / LLM workflow standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
csharp rules
jnpiyush/agentx · .cursor/rules/csharp.mdc · C# / .NET coding standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
python rules
jnpiyush/agentx · .cursor/rules/python.mdc · Python coding standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
react rules
jnpiyush/agentx · .cursor/rules/react.mdc · React / TSX frontend standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
typescript rules
jnpiyush/agentx · .cursor/rules/typescript.mdc · TypeScript / Node backend standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
agent-memory-systems skill
jnpiyush/agentx · .github/skills/ai-systems/agent-memory-systems/SKILL.md · Design agent memory beyond a single context window: short-term (working / scratchpad), long-term (episodic, semantic…
v1.0.0 · audit A · 16 stars
agent-observability skill
jnpiyush/agentx · .github/skills/ai-systems/agent-observability/SKILL.md · Instrument LLM agents with tracing, metrics, and evaluation telemetry. Use when adding OpenTelemetry GenAI semantic…
v1.0.0 · audit A · 16 stars
ai-agent-development skill
jnpiyush/agentx · .github/skills/ai-systems/ai-agent-development/SKILL.md · Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM…
git:20260903.b3f2610 · audit A · 16 stars
ai-evaluation skill
jnpiyush/agentx · .github/skills/ai-systems/ai-evaluation/SKILL.md · Use when evaluating AI quality, safety, completeness and cost with held-out tasks, executable graders, calibrated…
v1.1.0 · audit A · 16 stars
ai-safety-and-red-teaming skill
jnpiyush/agentx · .github/skills/ai-systems/ai-safety-and-red-teaming/SKILL.md · Defend LLM systems against prompt injection, jailbreaks, data exfiltration, and unsafe output. Covers input/output…
v1.0.0 · audit B · 16 stars
anthropic-claude skill
jnpiyush/agentx · .github/skills/ai-systems/anthropic-claude/SKILL.md · Implement production applications with Anthropic Claude models -- Messages API, tool use, prompt caching, extended…
v1.0.0 · audit A · 16 stars

Every file in jnpiyush/agentx

Browse by kind, by grade A, or by owner.