benchmark SKILL.md skillA
benchmark from gufranco/claude-engineering-rules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gufranco/claude-engineering-rules/benchmark@git:20261013.02cb8cdPins git:20261013.02cb8cd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gufranco/claude-engineering-rules
- Path
skills/benchmark/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261013.02cb8cd, committed Oct 13, 2026
- First version recorded
- Apr 4, 2026
- Size
- 7,009 bytes
- Repository stars
- 3
- License
- MIT
Measure API latency, bundle size, and database query time, and compare them against saved baselines to catch performance regressions.
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
## Overview Establishes performance baselines and detects regressions by comparing current measurements against stored reference values. ## When to Use Run before and after a change that can move latency, bundle size, or query time, and save a baseline from a known-good commit first, since a comparison needs one. | Invocation | Action | |-----------|--------| | `/benchmark` | Run all available measurement categories | | `/benchmark api` | Measure API endpoint latency only | | `/benchmark bundle` | Measure JS bundle size only | | `/benchmark db` | Measure database query time only | | `/benchmark --save` | Run all and save results as the new baseline | | `/benchmark api --save` | Run API latency and save as baseline | ## Process 1. Parse the invocation into categories and the `--save` flag; with no category, run all three. 2. Confirm the target is local or staging, then record the runtime version, tool version, and date in GMT. 3. Measure each requested category per Measurement Categories below. 4. When `.claude/benchmarks/<project>.json` exists, compare per Comparison and flag regressions against the threshold table. …
Read the whole file at its exact version.
How to install
mdr add gufranco/claude-engineering-rules/benchmark@sha256:698992dd25e5c55bThe line at the top of this page pins the label git:20261013.02cb8cd, 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_2essqfxlt54s6bga)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 4, 2026 and Oct 13, 2026, about one every 48 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.02cb8cd latest | 2026-10-13 | 02cb8cd | 7,009 B | A | view · diff |
| git:20261012.84ebb18 | 2026-10-12 | 84ebb18 | 6,897 B | A | view · diff |
| git:20260522.30b2aa6 | 2026-05-22 | 30b2aa6 | 4,870 B | A | view · diff |
| git:20260521.5220622 | 2026-05-21 | 5220622 | 4,864 B | A | view · diff |
| git:20260404.8042a93 | 2026-04-04 | 8042a93 | 4,844 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 (7009 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
gufranco/claude-engineering-rules · 3 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2essqfxlt54s6bga GET https://markdownregistry.com/api/v1/resolve?ref=gufranco/claude-engineering-rules/benchmark GET https://markdownregistry.com/api/v1/blob/698992dd25e5c55ba78b674f86415ba4885ab1a0d9623c3aa48d02518351632e
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 gufranco/claude-engineering-rules
Every file in gufranco/claude-engineering-rules