agent-evals SKILL.md skillA
agent-evals from ssheleg/agent-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ssheleg/agent-stack/agent-evals@git:20261025.28a0303Pins git:20261025.28a0303 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ssheleg/agent-stack
- Path
plugins/agent-stack/skills/agent-evals/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261025.28a0303, committed Oct 25, 2026
- First version recorded
- Oct 12, 2026
- Size
- 21,409 bytes
- Repository stars
- 4
- License
- MIT
Use when measuring whether an agent works: eval suites, trajectory judging, traces as regression fixtures, a calibrated LLM judge, release gates. Triggers: "agent eval" / "эвалы агента", "LLM judge" / "LLM-судья". Not for ordinary unit tests or model benchmarks; the loop is agent-orchestrator.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent evals — proving the thing behaves An agent's behaviour does not exist in its source. The code says what it is *allowed* to do; only a run says what it *did*. So the artifact under test is the execution record, and the suite runs on **two clocks**: the *observable* is authored up front, before the implementation exists, and the *corpus* it runs against is grown from production (§6). Three claims follow, and they are what makes this different from testing ordinary code: - **You are testing reasoning, not code paths**, so one granularity is never enough. - **Every natural-language input is unique**, so the edge cases cannot be enumerated offline. Production is not only where you catch what you missed — it is where you discover what to test for. - **Traces become test cases.** The corpus grows from what actually happened; the criterion it is measured against does not. --- ## Triggers "trajectory eval", "checker node", "is the agent getting better", "оценка агента", "как проверить агента". Moved here from the description in 0.31.3: "регрессионный набор". ## 1. Three primitives | Primitive | Is | Carries | |---|---|---| …
Read the whole file at its exact version.
How to install
mdr add ssheleg/agent-stack/agent-evals@sha256:8238e5d9e4b88dfeThe line at the top of this page pins the label git:20261025.28a0303, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cyqdseng4ebodxal)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 12, 2026 and Oct 25, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261025.28a0303 latest | 2026-10-25 | 28a0303 | 21,409 B | A | view · diff |
| git:20261023.244f284 | 2026-10-23 | 244f284 | 21,472 B | A | view · diff |
| git:20261020.672d5ff | 2026-10-20 | 672d5ff | 21,197 B | A | view · diff |
| git:20261019.baf2385 | 2026-10-19 | baf2385 | 21,601 B | A | view · diff |
| git:20261012.96ed0f8 | 2026-10-12 | 96ed0f8 | 20,773 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 (21409 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
ssheleg/agent-stack · 4 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cyqdseng4ebodxal GET https://markdownregistry.com/api/v1/resolve?ref=ssheleg/agent-stack/agent-evals GET https://markdownregistry.com/api/v1/blob/8238e5d9e4b88dfe9ed3104b080e6b72ddcfa8e9a71d025cbc2c582ab1c23033
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from ssheleg/agent-stack
Every file in ssheleg/agent-stack