arch-benchmark SKILL.md skillA
arch-benchmark from baristaze/swe_guidelines is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add baristaze/swe_guidelines/arch-benchmark@git:20260929.3422014Pins git:20260929.3422014 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- baristaze/swe_guidelines
- Path
skills/arch-benchmark/SKILL.md- Versions recorded
- 15
- Latest version
- git:20260929.3422014, committed Sep 29, 2026
- First version recorded
- Sep 20, 2026
- Size
- 16,654 bytes
- Repository stars
- 94
- License
- MIT
Run a benchmark scenario (a skill, a command, or a question) in a declared runtime and have frontier models score it against the rubric. Use to measure a change to a skill or the text.
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
# arch-benchmark
Measure a subject against a rubric and report what the judges said.
The harness is `benchmark/run.py` in a checkout of the guideline
repository, and it is the only thing that runs a benchmark. Do not
compose a provider call by hand, and do not invent a flag: every flag
is in `benchmark/README.md`, and `uv run benchmark/run.py --help`
prints them.
## Where it runs
The current working directory must be a checkout of the guideline
repository: `architecture.md`, `.claude-plugin/plugin.json`,
`benchmark/run.py`, and `benchmark/README.md` all present. Check with
`ls` before anything else. Otherwise stop and say so: the benchmark
measures the checkout it runs from, and writes its run folders under
that checkout's `benchmark/runs/<scenario>/`. The copy at `../..`, from
this skill's folder as `realpath` resolves it, is the installed plugin,
not a checkout; never run the harness from there.
## Input
The arguments are one of:
- a scenario name, with or without flags ("explain-tenancy",
"review-om with all four judges", "rehearse create-full-system",
"create-full-system with extras"), or the path of a scenario file,
which `--scenario` takes as it is;
…Read the whole file at its exact version.
How to install
mdr add baristaze/swe_guidelines/arch-benchmark@sha256:91f17dc1a2ef0d7bThe line at the top of this page pins the label git:20260929.3422014, 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_34wkbao5z7nw4ob7)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 15 versions of this file, between Sep 20, 2026 and Sep 29, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260929.3422014 latest | 2026-09-29 | 3422014 | 16,654 B | A | view · diff |
| git:20260929.30043dd | 2026-09-29 | 30043dd | 16,622 B | A | view · diff |
| git:20260928.53c4fbb | 2026-09-28 | 53c4fbb | 16,611 B | A | view · diff |
| git:20260928.3009fa9 | 2026-09-28 | 3009fa9 | 16,583 B | A | view · diff |
| git:20260928.bb9f385 | 2026-09-28 | bb9f385 | 14,549 B | A | view · diff |
| git:20260928.59ac174 | 2026-09-28 | 59ac174 | 12,246 B | A | view · diff |
| git:20260928.486f27f | 2026-09-28 | 486f27f | 12,128 B | A | view · diff |
| git:20260928.7fa6f2a | 2026-09-28 | 7fa6f2a | 11,368 B | A | view · diff |
| git:20260922.28cefc1 | 2026-09-22 | 28cefc1 | 4,460 B | A | view · diff |
| git:20260922.d0b19bf | 2026-09-22 | d0b19bf | 4,429 B | A | view · diff |
| git:20260922.e4ae97c | 2026-09-22 | e4ae97c | 4,173 B | A | view · diff |
| git:20260921.419a8e9 | 2026-09-21 | 419a8e9 | 4,370 B | A | view · diff |
| git:20260921.f72eecd | 2026-09-21 | f72eecd | 4,383 B | A | view · diff |
| git:20260921.93b5e1e | 2026-09-21 | 93b5e1e | 4,030 B | A | view · diff |
| git:20260920.65367e0 | 2026-09-20 | 65367e0 | 3,921 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 (16654 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
baristaze/swe_guidelines · 94 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_34wkbao5z7nw4ob7 GET https://markdownregistry.com/api/v1/resolve?ref=baristaze/swe_guidelines/arch-benchmark GET https://markdownregistry.com/api/v1/blob/91f17dc1a2ef0d7b2d46206459ce99a138a14ee7a44621504c19a661ab1573d0
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.