Expert Android & iOS PR review. Defaults to a PENDING (draft) GitHub review, or posts live on request. Ships 7 dedicated review agents (bug hunting, silent failures, code quality, 2026 platform deprecations, test coverage, comment accuracy, type design) for Kotlin/Compose, Swift/SwiftUI, and KMP.
★not rated 1 11d agoA
tokens not measured
originalMIT
Engineering standards for any code work on any stack — writing production code, slicing and reviewing PRs, authoring tests, running gates, merging, and running agent fleets.
★not rated 1
changed yesterdayA
tokens not measured
originalMIT
AI coding agent orchestrator for Claude Code — resolve GitHub issues end-to-end with isolated git worktrees and quality gates, through spec → exec → qa phases.
★not rated 1 yesterdayA
tokens not measured
originalMIT
PostToolUse hook that flags unnecessary comments. Runs comment-checker, then direnv exec if it is missing. Names flake.nix when that is why it is missing.
★not rated 1 5d agoA
tokens not measured
originalApache-2.0
A code-review pipeline that runs preliminary checks, sends code to specialised read-only checks, independently verifies findings, and makes a final decision.
Three-phase Claude Code Codex CLI collaboration workflow: Claude plans and writes the spec, Codex implements in the background, a fresh Codex session adversarially reviews the diff. For code changes that deserve a written spec.
★not rated 1 2mo agoA
tokens not measured
originalMIT
A thinking partner for Claude Code. The instrument you reach for when you want to pause, get a second perspective, or check the assumptions baked into what you're about to ship. Adds /quill:consult, /quill:perspective, and /quill:assumptions slash commands.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Odoo SA development skills, hooks, and conventions for PSDU customer work. Principles-first guidance for module development, code review, testing, and continuous skill refinement.
Fact-check every agent turn against the real code, the working-tree git diff, and recorded test runs. Deterministic, cited Supported/Contradicted/Refused verdicts — contradictions block the turn so the agent corrects itself before you read it. Requires the truth binary (the SessionStart hook tells you how to install…
★not rated 1 2mo agoA
tokens not measured
originalMIT
Review every code change before the turn ends: fresh-context reviewer agents, a verified finding standard, honest convergence, and a measured token budget — enforced by a Stop hook, graph-aware when you have a code graph, zero-cost when you don't.
★not rated 1
changed todayA
tokens not measured
originalMIT
Automatic code review powered by OpenAI Codex CLI. Codex reviews your plans and code as a second opinion — like having a senior engineer look over Claude's shoulder.
★not rated 0▲
+1 5mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: