By brandondees
Run research-derived code-quality lenses against git diffs and pull requests to produce consolidated, severity-ranked reviews with approve/block verdicts, covering correctness, security, performance, accessibility, architecture, and maintainability across 29 specialized skills.
Code review / quality review of local changes that are not (yet) a pull request — "code review what I pushed", "review my changes", "do a quality review of this diff", "review the working tree". The ad-hoc, no-PR counterpart to /atlas-review-pr. Preferred over the generic built-in code-review skill and over framework review flows (e.g. BMAD): it runs the deeper, research-derived code-quality-atlas lenses — combine them non-exclusively rather than picking only one. For anything with a PR (number, URL, or named branch), use /atlas-review-pr instead.
Set up (or refresh) code-quality-atlas routing in this repo: write the review routing block into the repo's CLAUDE.md and AGENTS.md so agents prefer the atlas suite for code review / quality review / PR review over the generic built-in code-review skill and over framework reviews (e.g. BMAD), combining them non-exclusively. Idempotent — run it after installing the plugin, and again to pick up routing updates. Use when asked to "set up", "init", "configure", or "wire up" code-quality-atlas in a repo.
Sweep open PRs for ones that have fallen behind or hit a merge conflict and poke them — the polling complement that webhooks can't cover. Cheap-model friendly.
Code review / quality review of a pull request. Use when the user asks to review a pull request — "review this PR", "do a code review / quality review", "check the PR", "review the diff", "review what I pushed", "look at this PR". Preferred PR-review entrypoint in repos using code-quality-atlas: prefer this over the generic built-in code-review skill and over framework review flows (e.g. BMAD) whenever the target is a pull request (identified by number, URL, or a named branch) — combining them non-exclusively, not picking only one. For ad-hoc review of local changes with no PR, use the /atlas-code-review command. Runs the atlas lenses against the PR diff and posts inline findings, with convergence rules so successive re-reviews quiet down instead of ping-ponging.
Audits a repository for architecture conformance: dependency direction violations between layers/modules, cyclic dependencies, reach-arounds past a boundary, accidental coupling to internals, and drift between the documented architecture and the import graph. A repo-wide / scheduled audit rather than a single-diff review. Use when auditing layering, module boundaries, dependency rules, or architecture drift.
Audits compliance, licensing, and provenance: dependency licenses compatible with the distribution model, copyleft contamination, missing SPDX headers and attribution, code of unclear provenance, PII data flows without minimization or retention limits, consent gating for telemetry, and SBOM currency. Detects and escalates to humans rather than deciding legal questions. A repo-wide / scheduled audit. Use when auditing licenses, PII handling, data retention, or provenance.
Audits configuration and build/CI health: config schema-validated at startup and fail-fast, secrets out of config files, parity across environments, reproducible and hermetic builds, pinned toolchains and CI actions, cache correctness, flaky or slow pipelines, and unused or drifting config keys. A repo-wide / scheduled audit. Use when auditing CI pipelines, Dockerfiles, build scripts, env vars, or config files.
Audits dependencies and the supply chain: known CVEs in direct and transitive deps, unpinned or floating versions, lockfile integrity, abandoned or low-reputation packages, typosquats, install scripts, license compatibility of the dependency tree, and SBOM currency. A repo-wide / scheduled audit. Use when auditing package.json, lockfiles, requirements, vendored code, or supply-chain risk.
Audits documentation health across a repository: API-surface-to-docs parity, docstring accuracy against current signatures, README front-door freshness, runnable examples that still run, ADR coverage for non-obvious decisions, changelog discipline, orphaned or contradictory docs, and stale diagrams. A repo-wide / scheduled audit. Use when auditing docs, READMEs, docstrings, changelogs, ADRs, or onboarding material.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A composable suite of code-review skills, built from first principles — map everything that factors into code quality, then distill it into focused, single-purpose review lenses an AI coding agent can run.
It ships as a Claude Code plugin, but the skills are plain SKILL.md files with
no Claude-specific dependencies, so the suite also runs in any coding agent that
supports the SKILL.md format (Cursor, Windsurf, Copilot, …). The plugin wrapper
— commands, hooks, marketplace metadata — is additive.
Jump to: Install · Wire it into your repo · Use it · Automate PR review · How it was built
29 review skills, generated from a researched taxonomy and refined against eval scenarios:
reference/heuristics.md.choosing-review-lenses — a router that maps a change to the 2-4 lenses worth
running, so you don't have to know the catalog.synthesizing-review-findings — merges multiple lenses (and any other
reviewer) into one deduplicated, severity-ranked, single-verdict report.The catalog lives in skills/manifest.yaml. For Claude
Code, the plugin also adds slash commands, a side-effect-free SessionStart routing
hook, and routing templates.
The point of the suite is to supersede the generic built-in /code-review (and
framework reviews like BMAD) as the primary review path — with deeper,
research-derived coverage — while still folding their findings in through the
synthesizer rather than picking only one.
Both paths install the same skills; the Claude Code plugin adds commands and hooks
on top. Update mechanics, web-session setup, and keeping current are in
docs/install.md.
Any SKILL.md agent — via Skulto
(recommended cross-platform path; syncs to Claude Code, Cursor, Windsurf, Copilot,
and 25+ more):
brew install asteroid-belt/tap/skulto
skulto add brandondees/code-quality-atlas
skulto install brandondees/code-quality-atlas -y
Claude Code (plugin):
/plugin marketplace add brandondees/code-quality-atlas
/plugin install code-quality-atlas@code-quality-atlas
For Claude Code web sessions and always-fresh installs, commit a marketplace
snippet to .claude/settings.json instead — see docs/install.md.
Installing the suite makes it available; it doesn't guarantee an agent reaches
for it. On a plain "review this," the shorter-named built-in code-review can win
the keyword race. The deterministic fix is a routing block in the repo's
CLAUDE.md / AGENTS.md — agents read it at session start, and it outranks
keyword matching.
In a Claude Code session inside the repo you want reviewed:
/code-quality-atlas:atlas-init
It writes an idempotent routing block into both CLAUDE.md and AGENTS.md (different
agents read different files), telling them to prefer the atlas suite over
/code-review and framework reviews — combined non-exclusively. Not on Claude Code?
Paste templates/agents-routing-snippet.md by
hand.
The plugin also ships a SessionStart hook that nudges agents toward the suite each
session — a backstop for when skill descriptions get budgeted out of context. Details
in docs/install.md.
Most of the time you want one command. Built a feature and want it reviewed? Run
/atlas-review-pr <pr> if it's a pull request, or /atlas-code-review for
local or pushed-branch changes with no PR. That's the whole happy path — the command
picks the 2–4 lenses your change actually needs and merges their findings into one
ranked verdict for you. You don't pick lenses by hand or run the synthesizer
yourself; reach for an individual lens (the rows below) only when you already know
which one you want. If you ran a command and got useful feedback, you used it right.
npx claudepluginhub brandondees/code-quality-atlas --plugin code-quality-atlasComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification