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
mdr add jnpiyush/agentx/experimentation-loop@v1.1.0mdr add jnpiyush/agentx/experimentation-loop@sha256:14a05da1300d7bd2Pin 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.
[](https://markdownregistry.com/a/art_67h3kvtnbd32pbr6)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-15 | f17c505 | 14,339 B | A | view · diff |
| v1.1.0 | 2026-05-22 | c9b598a | 14,337 B | A | view · diff |
| v1.0.0 | 2026-04-29 | 1c1ff57 | 9,172 B | A | view · diff |
| v1.0.0 | 2026-04-28 | 21e2bfe | 8,129 B | A | view |
Audit of the latest version
- 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
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.