kitaru-replay-experiment skillA
kitaru-replay-experiment is agent-read markdown (skill) from zenml-io/kitaru-skills: Run and interpret one safe, bounded Kitaru replay comparison against an accepted cohort and exact evaluators. Use when a user wants to replay a cohort, test or compare a model, prompt, system prompt, parameter, agent version, or tool policy, supervise an experiment run, determine whether one candidate helped, or ask for one bounded change worth testing..
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
# Kitaru replay experiment Test one candidate condition against known cases and explain whether the available evidence improved, regressed, traded off, or stayed inconclusive. Do not make the deployment decision. ## Core contract - Start from an accepted behavior, exact cohort version, exact evaluator versions and parameters, and one candidate change. Suggest one bounded candidate only when asked. - Replay starts a fresh agent task from each historical session's stored top-level inputs after applying the override. It does not restore an arbitrary checkpoint, conversation, process memory, adapter instance state, filesystem, or external world state. - Resolve adapter support and its construction path before asking to run the experiment. A shared replay schema does not prove that an adapter supports a requested override or tool source. - Require an explicit tool policy for every tool-using run. Omission resolves to live passthrough on the current server and is unsafe as an implicit default. - Carry exact IDs, versions, evaluator parameters, run-spec evidence, tool policy, failures, and missing results forward. …
Read the whole file at its exact version.
How to install
mdr add zenml-io/kitaru-skills/kitaru-replay-experiment@git:20260903.598f4b2mdr add zenml-io/kitaru-skills/kitaru-replay-experiment@sha256:bb4f2c6bc6eeeaefPin 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_vt65qkjp5svgrhak)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260903.598f4b2 latest | 2026-09-03 | 598f4b2 | 14,702 B | A | view · diff |
| git:20260902.d9aba70 | 2026-09-02 | d9aba70 | 14,304 B | A | view · diff |
| git:20260902.1e2a1a9 | 2026-09-02 | 1e2a1a9 | 14,135 B | A | view · diff |
| git:20260825.ed9c6c3 | 2026-08-25 | ed9c6c3 | 13,737 B | A | view · diff |
| git:20260825.9c0e2f1 | 2026-08-25 | 9c0e2f1 | 13,379 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 (14702 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
zenml-io/kitaru-skills · 5 stars · license Apache-2.0 · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vt65qkjp5svgrhak GET https://markdownregistry.com/api/v1/resolve?ref=zenml-io/kitaru-skills/kitaru-replay-experiment GET https://markdownregistry.com/api/v1/blob/bb4f2c6bc6eeeaef820cc9405ad9e4bdb09933c081cbf9ecd8af1217de1abd79
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.