eval-runner SKILL.md skillA
eval-runner from haabe/mycelium is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add haabe/mycelium/eval-runner@git:20260704.7639f18Pins git:20260704.7639f18 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- haabe/mycelium
- Path
plugins/mycelium/skills/eval-runner/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260704.7639f18, committed Jul 4, 2026
- First version recorded
- May 9, 2026
- Size
- 4,277 bytes
- Repository stars
- 51
- License
- MIT
Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.
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 Runner Benchmark the agent's performance against defined scenarios. Adapted from n-trax eval system. ## Commands ### `run <category/name>` 1. Read YAML from `.claude/evals/scenarios/<category>/<name>.yml` 2. Parse fields (name, category, task_prompt, success_criteria, budget) 3. Execute setup steps if defined 4. Record start time 5. Execute task via reflexion workflow (read corrections first) 6. Record end time and iteration count 7. Validate ALL success criteria 8. Write result JSON to `.claude/evals/results/<timestamp>-<name>.json` 9. Report summary ### `run-all [category]` 1. Glob `.claude/evals/scenarios/**/*.yml` 2. Skip scenarios with `status: retired` 3. For each: run in isolation (git stash), record result, restore 4. Update `.claude/evals/pass-history.json` with each result 5. Aggregate and report ### `run-split <optimization|holdout>` 1. Glob `.claude/evals/scenarios/**/*.yml` 2. Read each YAML, filter by `split` field matching the requested set 3. Skip scenarios with `status: retired` 4. For each matching scenario: run in isolation, record result, restore 5. Update `.claude/evals/pass-history.json` with each result …
Read the whole file at its exact version.
How to install
mdr add haabe/mycelium/eval-runner@sha256:f398c17e0461ce51The line at the top of this page pins the label git:20260704.7639f18, 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_5vgmtxhbn3g5pz24)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 9, 2026 and Jul 4, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260704.7639f18 latest | 2026-07-04 | 7639f18 | 4,277 B | A | view · diff |
| git:20260525.9fac942 | 2026-05-25 | 9fac942 | 4,277 B | A | view · diff |
| git:20260522.1825b22 | 2026-05-22 | 1825b22 | 3,967 B | A | view · diff |
| git:20260509.70c07fb | 2026-05-09 | 70c07fb | 3,953 B | A | view · diff |
| git:20260509.4656910 | 2026-05-09 | 4656910 | 3,937 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 (4277 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
haabe/mycelium · 51 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5vgmtxhbn3g5pz24 GET https://markdownregistry.com/api/v1/resolve?ref=haabe/mycelium/eval-runner GET https://markdownregistry.com/api/v1/blob/f398c17e0461ce517d24b9d61981a568500acd9ea89b6a6ccd8c49d31fdebfdf
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.