▸ This tool was built by an AI agent from Zoral
← RATE MY GITHUB

#107 — Top 93.1%

zexoverz

Faisal Firdani

B

Solid engineer

Overall

0.0

/ 100

01 · Roasts

Forks did the talking

ETHJKT x UNPAM pulled 54 forks on 5 stars—teaching distribution is carrying the adoption stat like a group-project MVP.

Standards lab, not shipping lane

Three Solidity reference repos have serious tests and specs, but two still sit at zero stars and zero forks.

Fresh paint, short runway

grid-workshop-scaffold is impressively equipped, but its under-30-day history means the architecture has not had time to earn long-haul scars.

The graveyard is real

65% stale repositories says the account has history; 388 commits and a September push say the protocol-engineering era is still very much alive.

Built using

Zoral

Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.

zoral.ai

02 · Category breakdown

  • Impact
    25% weight
    66C
  • Consistency
    20% weight
    60C
  • Quality
    20% weight
    75B
  • Depth
    15% weight
    62C
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    55D

03 · Stats

365-day commit heatmap

306 active days

Less
More

Language distribution

7 langs
  • JavaScript31%
  • Solidity27%
  • CSS22%
  • TypeScript11%
  • HTML6%
  • SCSS1%
  • Other2%

04 · Numbers

Owned repos

non-fork

63

Commits

last 12 months

388

Followers

129

Joined GitHub

Apr 2019

05 · Top repos

zexoverz /

grid-workshop-scaffold

68/100

Documented, typed TypeScript workshop scaffold delivering five AI-agent archetypes with REST/MCP consoles, mock data, schema validation, fallbacks, tests, and VM deployment automation.

I48Q78D62
READMETestsCITyped
HTML02mo ago

zexoverz /

confidential-agent-policy-verdicts

52/100

A thoroughly documented Solidity/Noir reference implementation for confidential agent-policy verdicts, with a tested Guard, domain registry, denial anchors, generated UltraHonk verifier, and real-proof integration fixtures; adoption remains early at 1 star.

I23Q68D50
READMETestsCI
Solidity1this week

zexoverz /

airbnb-clone

48/100

A documented, typed Next.js 13 Airbnb marketplace demo with Prisma/MongoDB, multi-provider auth, listings, search, favorites, and reservations; it has a deployed Vercel URL but only 1 star and lacks tests and CI.

I30Q60D50
READMETyped
TypeScript12mo ago

zexoverz /

ethjkt-unpam-learning-kit

42/100

A documented ETHJKT x UNPAM teaching kit combining five-day learning materials, a browser shopping/security exercise, and a Sepolia KampusSwap demo with Solidity contracts and a React wallet UI.

I48Q43D35
README
JavaScript51mo ago

zexoverz /

reference-relative-slippage-bounds

40/100

A focused Solidity ERC draft reference with live Chainlink integration, balance-delta enforcement, and a well-specified Foundry test suite, but no demonstrated adoption or CI.

I22Q62D35
READMETests
Solidity011d ago

zexoverz /

erc-8373-onchain-consumer

34/100

A focused Solidity reference implementation for ERC-8373 with a readable cutoff enforcer, tri-state evidence model, 17 behavior tests, and replay of nine published v1 conformance cases; adoption is not yet demonstrated.

I20Q45D35
READMETests
Solidity0this week

zexoverz /

zexo-harness-template

32/100

A documented Claude Code harness template with 6 subagents, 9 slash-command skills, vendored ECC rules, MCP configuration, shell hooks, setup automation, and GitHub Actions CI; it is newly shipped with no visible adoption yet.

I20Q55D20
READMECI
Shell01mo ago

zexoverz /

zexoverz

23/100

A low-adoption GitHub profile repository with 3 stars and a README presenting the author’s Web3 background, tools, and external work references, but no sampled source files or engineering infrastructure.

I20Q20D35
README
Unknown313d ago

zexoverz /

grid-workshop-scaffold-2

2/100

Empty repository scaffold with no files, documentation, activity, or observable implementation.

I5Q0D5
Unknown02mo ago

06 · Timeline

  1. Apr 29, 2019
    Joined GitHub
  2. Jan 6, 2021
    Created zexoverz
  3. May 16, 2023
    Created airbnb-clone — This is a repository for a Full Stack Airbnb Clone with Next.js 13 App Router: React, Tailwind, Prisma, MongoDB, NextAuth.
  4. May 25, 2026
    Created grid-workshop-scaffold — One Man Team Workshop · Real World AI Agent Hackathon — Pre-Event Experience The Solopreneur Stack — Building a One-Person Company with AI Agents.
  5. Jun 17, 2026
    Created grid-workshop-scaffold-2
  6. Jul 5, 2026
    Created ethjkt-unpam-learning-kit — Learning kit persiapan H-1 untuk Short Course AI & Blockchain ETHJKT x UNPAM
  7. Jul 20, 2026
    Created zexo-harness-template — Best-in-world personal harness for Claude Code — 6 subagents, 9 slash commands, MCP servers, RTK, ECC, plugin format. Fork it, run one command, get productive.
  8. Jul 29, 2026
    Created confidential-agent-policy-verdicts — Reference implementation of the draft ERC Confidential Agent Policy Verdicts — pre-execution ZK allow/deny for autonomous agent actions against a committed secret policy.
  9. Aug 5, 2026
    Created reference-relative-slippage-bounds — Reference implementation for the Reference-Relative Slippage Bounds ERC draft (interface + floor logic + ERC-7726 adapter + fork test)
  10. Aug 19, 2026
    Created erc-8373-onchain-consumer — On-chain consumer for ERC-8373 Post-Quantum Anchored Key-Binding: interface, reference cutoff enforcer, and tests driven by the published conformance vectors
  11. Sep 2, 2026
    Most recent push to confidential-agent-policy-verdicts

07 · Compare

github.com/
zexoverz · 6dmedian coder

08 · Rubric

How this score was produced

Overall = Σ (category × weight) + gentle top-end curve

CategoryWeightScoreContrib.
Raw total64.8
Top-end curve+5.7
Final overall70.5

Tier thresholds

S90100Mass-producing humansA8089Ship machineB7079Solid engineerC6069Getting thereD4059README enthusiastF039GitHub tourist
▸ How the pipeline works
  1. 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
  2. 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
  3. 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
  4. 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
  5. 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.

~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.

▸ Data sources & caveats
  • Heatmap & commit totals: GitHub GraphQL contributionsCollection — covers the last 365 days, includes private repos when the user has opted in (default).
  • Language %: byte totals across the top 30 owned non-fork repos.
  • Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
  • Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.
zexoverz · 70.5/100 — Rate My GitHub