haenv-bench SKILL.md skillA
haenv-bench from thetahealth/mirobody-env is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add thetahealth/mirobody-env/haenv-bench@git:20261018.f879c17Pins git:20261018.f879c17 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- thetahealth/mirobody-env
- Path
skills/haenv-bench/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261018.f879c17, committed Oct 18, 2026
- First version recorded
- Sep 30, 2026
- Size
- 8,099 bytes
- Repository stars
- 179
- License
- MIT
Run models against an existing question pack and produce a board: offline smoke tests, real models, resumable runs, per-batch archiving, how to read cost, how to read the artifacts (eval/responses/**trace**/cases/batch), and why changing a judge means recomputing, not re-running. Triggers when the user says things like "run an eval batch", "produce a report", "backfill a model", "how much did this batch cost", "show a model's tool-call trace".
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
# haenv-bench — run a question pack against models: evaluation · resumable runs · cost · boards **One line**: the question pack is already on disk; this skill covers how to turn it into a board, and how to read the artifacts once it's done. Companion skills: `haenv-synth` (generating question packs and data) · `haenv-extend` (adding your own judge). Warning: this file is an index, not the sole source of truth. The full reproduction steps are in `docs/REPRODUCE.md`; what each judge measures is in `docs/design/judges-explained.md`. Every command here has actually been run. --- ## 1. Running it ```bash uv run haenv run benchmarks/inputs/example-ew.job.yaml --offline # smoke test: only offline deterministic stubs, zero cost uv run haenv run benchmarks/inputs/example-ew.job.yaml --models A --limit 1 # real model, verify one cell first uv run haenv run benchmarks/inputs/example-ew.job.yaml # full run (config.default_models x every case) ``` Don't leave a long run attached to your session: ```bash nohup uv run haenv run benchmarks/inputs/example-ew.job.yaml > /tmp/haenv.out 2>&1 & ``` …
Read the whole file at its exact version.
How to install
mdr add thetahealth/mirobody-env/haenv-bench@sha256:67122a83200f7febThe line at the top of this page pins the label git:20261018.f879c17, 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_t7kdedt4puctx42o)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 30, 2026 and Oct 18, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.f879c17 latest | 2026-10-18 | f879c17 | 8,099 B | A | view · diff |
| git:20261001.a7c31a5 | 2026-10-01 | a7c31a5 | 7,682 B | A | view · diff |
| git:20260930.9b6ec39 | 2026-09-30 | 9b6ec39 | 7,750 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 (8099 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
thetahealth/mirobody-env · 179 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_t7kdedt4puctx42o GET https://markdownregistry.com/api/v1/resolve?ref=thetahealth/mirobody-env/haenv-bench GET https://markdownregistry.com/api/v1/blob/67122a83200f7feb91af587fda77e5223b06185557cd7cab24d5921fa20e8c8a
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.