eval-guide SKILL.md skillA
eval-guide from coder/agent-tty is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add coder/agent-tty/eval-guide@git:20260419.3600abbPins git:20260419.3600abb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- coder/agent-tty
- Path
.mux/skills/eval-guide/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260419.3600abb, committed Apr 19, 2026
- First version recorded
- Apr 16, 2026
- Size
- 8,238 bytes
- Repository stars
- 30
- License
- Apache-2.0
Guide for running statistically meaningful agent-tty evals with trials, parallelism, and A/B comparison. Covers non-determinism baseline, recommended sample sizes, and result interpretation.
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
# Eval Guide Use this guide when you are trying to answer **"did this skill or prompt change actually help?"** for `agent-tty` evals. The short version: **do not trust a single run**. This eval stack now supports multi-trial sampling, parallel execution, trial aggregation, and paired baseline comparison because the underlying model behavior is noisy enough that one pass/fail result is not decision-grade. ## 1. What we learned about eval non-determinism - Identical serial reruns showed a **~15-17% pass/fail flip rate** in practice, across both Codex and Claude runs. - Scores moved even more often than hard pass/fail: **~30-39% of identical reruns changed score**. - The movement was directionally balanced, which is the important point: this looked like **noise**, not a systematic drift up or down. - Cross-provider checks reinforced that conclusion: in the parallel safety analysis, **Codex and Claude shared zero common regressions**, which is strong evidence that parallelism itself was not introducing consistent failures. - Treat these findings as the baseline noise floor. If your "improvement" is smaller than that noise, it is not persuasive. …
Read the whole file at its exact version.
How to install
mdr add coder/agent-tty/eval-guide@sha256:9068c85a8060d907The line at the top of this page pins the label git:20260419.3600abb, 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_o7npea5utb4fzqzc)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 16, 2026 and Apr 19, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260419.3600abb latest | 2026-04-19 | 3600abb | 8,238 B | A | view · diff |
| git:20260416.02cc7dd | 2026-04-16 | 02cc7dd | 6,997 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 (8238 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
coder/agent-tty · 30 stars · license Apache-2.0 · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_o7npea5utb4fzqzc GET https://markdownregistry.com/api/v1/resolve?ref=coder/agent-tty/eval-guide GET https://markdownregistry.com/api/v1/blob/9068c85a8060d907ae56eabeb7b1f0c67913a0652e7289bb3537edb42af7c260
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.