brain-score SKILL.md skillA

brain-score from stuinfla/ruvnet-brain is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stuinfla/ruvnet-brain/brain-score@git:20260727.720a4bf

Pins git:20260727.720a4bf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stuinfla/ruvnet-brain
Path
plugin/skills/brain-score/SKILL.md
Versions recorded
3
Latest version
git:20260727.720a4bf, committed Jul 27, 2026
First version recorded
Jul 10, 2026
Size
7,265 bytes
Repository stars
83
License
a license file GitHub does not identify

Score ANY repository 0-100 across 8 dimensions using the exact evidence-or-it-didn't-happen scorecard RuvNet-Brain applies to itself. Use when the user says "score this repo", "score my repo", "scorecard", "brain-score", "how good is this codebase", "rate this project", "audit quality", or asks for an honest 0-100 quality assessment of a repository. Every deduction must cite evidence from the actual repo; a known architectural flaw caps its dimension at ≤70; a "what I did NOT test" section is…

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

# Brain-Score — the 8-dimension repo scorecard (0–100)

Score the repo in front of you the way RuvNet-Brain scores itself: **gates that could have failed,
before scores that can be believed.** A score is only real if the evidence behind it was collected
by running real commands against the actual repo — never from memory, never from vibes, never from
what the README promises.

These same rules are the phase-gate grader inside `/brain-build` (the autonomous build contract:
loop each phase to ≥95 under brain-score rules, max 5 iterations — see the `brain-build` skill).

## Non-negotiable scoring rules

1. **Every deduction cites evidence.** Each point lost names the file/line, the command you ran and
   its output, or the artifact you inspected. "Feels incomplete" is not a deduction; `"tests/ has 3
   files, 2 contain zero assertions (tests/foo.test.js:1-40)"` is.
2. **A known architectural flaw caps its dimension at ≤70** — no matter how much else in that
   dimension works. (Example: a quality gate whose sample size cannot statistically detect the
   regression it exists to catch caps reliability at 70, even with green CI.)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stuinfla/ruvnet-brain/brain-score@sha256:a130c51f4f2e980a

The line at the top of this page pins the label git:20260727.720a4bf, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_btq7rkkqv4yvowyq.svg)](https://markdownregistry.com/a/art_btq7rkkqv4yvowyq)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jul 10, 2026 and Jul 27, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20260727.720a4bf latest2026-07-27 720a4bf 7,265 BA view · diff
git:20260710.ca9d6022026-07-10 ca9d602 7,245 BA view · diff
git:20260710.9ce2a582026-07-10 9ce2a58 7,046 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7265 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

GitHub

stuinfla/ruvnet-brain · 83 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_btq7rkkqv4yvowyq
GET https://markdownregistry.com/api/v1/resolve?ref=stuinfla/ruvnet-brain/brain-score
GET https://markdownregistry.com/api/v1/blob/a130c51f4f2e980a0d214400ecab0c8da2b94e803a5b32ae73adab6d68f01635

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 stuinfla/ruvnet-brain

llms-full.txt@explainer llms.txt file
stuinfla/ruvnet-brain · explainer/llms-full.txt
git:20261030.1cf31b5 · audit A · 83 stars
llms.txt@explainer llms.txt file
stuinfla/ruvnet-brain · explainer/llms.txt
git:20261030.1cf31b5 · audit A · 83 stars
brain-build SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/brain-build/SKILL.md · The autonomous build contract, out of the box — "/brain-build <what you want>" activates the disciplined hands-off…
git:20260727.720a4bf · audit A · 83 stars
brain-console SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/brain-console/SKILL.md · Open the RuvNet Brain Console (RNBC) for "/rnbc", "/rnb", "/rvbc", "/rvcb", "/brain-console", or…
git:20261001.a5f64b8 · audit A · 83 stars
brain-prompt SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/brain-prompt/SKILL.md · Metaprompting assistant — "/brain-prompt <rough idea>" turns a rough ask into "the right prompt": a complete, tuned…
git:20260727.720a4bf · audit A · 83 stars
release-proof SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/release-proof/SKILL.md · Fail-closed exact-artifact release and deployment authority. Use before saying a release is ready, pushing a release…
git:20260920.7e8753f · audit A · 83 stars
rnbc SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/rnbc/SKILL.md · Open the RNBC — RuvNet Brain Console — in Claude Code and Codex when the user says "rnbc", "rnb", "Configure RuvNet…
git:20261001.a5f64b8 · audit A · 83 stars
ruvnet-brain SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/ruvnet-brain/SKILL.md · Use for ANY request to build, add, implement, design, plan, refactor, fix, speed up, secure, test, or cut the cost of…
git:20261025.9bd22f3 · audit A · 83 stars
rvbc SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/rvbc/SKILL.md · Open the RuvNet Brain Console in Claude Code and Codex when the user says "Configure RuvNet Brain", mentions "rvbc" or…
git:20261001.a5f64b8 · audit A · 83 stars
savings SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/savings/SKILL.md · Show the MetaHarness routing ledger inline — which model each task was routed to, what it displaced, and the percentage…
git:20260727.720a4bf · audit A · 83 stars
whats-new SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/whats-new/SKILL.md · Explain what is new in the installed RuvNet Brain release from live version metadata and the curated release notes. Use…
git:20260801.5631618 · audit A · 83 stars
tri-smart SKILL.md skill
stuinfla/ruvnet-brain · tri-smart-skill/tri-smart/SKILL.md · Use whenever the user says "use TriSmart", "tri smart", "trip smart", "use Dual", "dual smart", "use ModelMesh", "model…
v1.1.0 · audit A · 83 stars

Every file in stuinfla/ruvnet-brain

Browse by kind, by grade A, or by owner.