richfrem/agent-plugins-skills · plugins/agent-agentic-os/skills/os-eval-runner/SKILL.md

os-eval-runner skillA

os-eval-runner is agent-read markdown (skill) from richfrem/agent-plugins-skills: Stateless evaluation engine that scores and gates skill improvement iterations using headless Python evaluation scripts. Use when the user says "evaluate this skill", "run autoresearch loop on", "optimize this skill", "run the eval loop", or when another agent proposes a change and needs validation..

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.

How to install

Latest version
mdr add richfrem/agent-plugins-skills/os-eval-runner@git:20260628.325c1b7
Exact content
mdr add richfrem/agent-plugins-skills/os-eval-runner@sha256:be78ba4c14e0cf65

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_gx6e4uaxpduo3t4x.svg)](https://markdownregistry.com/a/art_gx6e4uaxpduo3t4x)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260628.325c1b7 latest2026-06-28 325c1b7 4,025 BA view · diff
git:20260607.23c573b2026-06-07 23c573b 25,183 BA view · diff
git:20260601.c08662d2026-06-01 c08662d 25,099 BA view · diff
git:20260427.a7c1e492026-04-27 a7c1e49 25,102 BA view · diff
git:20260427.62fade32026-04-27 62fade3 25,077 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 (4025 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

richfrem/agent-plugins-skills · 6 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gx6e4uaxpduo3t4x
GET https://markdownregistry.com/api/v1/resolve?ref=richfrem/agent-plugins-skills/os-eval-runner
GET https://markdownregistry.com/api/v1/blob/be78ba4c14e0cf65fb9439a88a955c04ae490063c3ab8a2b729d669181872d8d