Claude Code Code Review and Testing Mods

Runs proof-driven bug hunt rounds that must prove a bug before fixing it

Flag JSON, YAML, TOML and .env parse errors right after an edit

Flag the doc lines a git commit makes stale and track them until the docs hold again

Runs tests and lint after file edits and shows a badge with each failure's location

Reports translation keys your locale files lack after each edit

Flag edits that build SQL by joining strings and name the exact lines

Benjamin's collection of Claude Code skills — daily workflow, code quality, dev tools, and specialist agents

Milestone-driven development workflow and tracking system for Claude Code projects: a language-agnostic core with per-repo toolchain profiles (R…

An IDE-style file tree that shows what Claude reads, edits and commits, with git status, search and a file preview

Test-first workflow for coding agents, without the spec ceremony

Line-by-line review pane: comment on what Claude changed, then send every comment back as one prompt

Optional PREVIEW console for Claude Code that observes Skill Heaven summons and never changes them: a status entry, a Lens band above the prompt, and…

Compacts at the right moment: after a commit or green tests, a minute before the prompt cache expires, or when Claude asks for it with its own…

Learn English from your daily Claude Code use: an ESOL coach that logs nativized corrections of your English prompts to a local learning log, with a…

An orchestrated build workflow for Claude Code on Orca: one orchestrator session, one Builder per batch in its own worktree, review passes until GO…

A debugger for Claude Code tool calls: breakpoints, pause/continue/reject/step, a timeline, an inspector, Error Lens failure diagnosis, a Permissions…

A workspace pane for Claude Code: vitals rail, edit gate (blocks Edit, Write, NotebookEdit and MultiEdit until you approve; not Bash or MCP tools)…

Claude Code, with receipts

Copilot-style review of the files Claude changes: a tree of changed files with +/- counts, accept/reject per file, folder or all, and a VS Code diff…

A live preview pane beside the transcript: the session's diff with review comments, and rendered plans and docs as Claude writes them

Sessiondeck: Flightdeck's live session dashboard plus prompt, cache, tool latency, hot files, tests, aborts, and a chart band for context and up to a…

The debugging proxy Claude can read, inside Claude Code on macOS: HTTPS, HTTP/2, gRPC, WebSockets and server-sent events from the browser, iOS and…

Preview 3D Gaussian splats (.ply, .spz, .splat, .ksplat, .sog) in a Claude Code pane: orbit with the mouse, rendered by Spark in headless Chrome

Adversarial review of a PR, plan or document by an isolated reviewer that never sees the author's context, with a triage pane deciding which findings…

A council of independent code reviewers (Codex, Pi, Devin, OpenCodeReview) runs over your working diff in parallel; one summary of agreements…

Keeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, protected paths with an approval log…

Second opinions inside Claude Code: GPT as fresh eyes when you go in circles, Codex acceptance of every handover, and Codex+Claude review of each…

Token-light team companion: capped agent teams, risk-based review, disciplined debugging

Holds prompts, @file contents and Read results that contain PII or secrets behind a review pane with per-type allow/redact decisions

An inbox for review requests, your own PRs and your issues (assigned to you or created by you): AI summary and risk, an AI review that can approve, a…

PR Pulse: live status, merge readiness, checks, comments, review queue and change alerts for your GitHub PRs, with a collapsible band

A pane beside the transcript with the GitHub pull requests and issues related to the current session: drag a title or description to leave a comment…

Which files each Claude Code agent has in its context, and how much of each: line ranges, tokens, re-reads, edits, and which files only a subagent it…

Ships a feature only when a test that actually ran proves every requirement in its spec

Keeps a GitHub Spec Kit feature and its code tied together inside Claude Code: a new idea researched and shaped with you (or your PRD reviewed and…

One typed command runs the work: /agt plans, builds and reviews with the right model per step, steps aside on small tasks, and ends on one short card

Claude records each assumption it makes; review them in a side pane, mark them right or wrong, and the verdicts go back to Claude

Session metrics and reply themes for the Claude Code desktop: context, cost, rate limits, cache, tools and subagents, as a status line, a progress…

Multi-agent orchestrator harness for Claude Code: command loop, ledger, dispatch protocol, review cycle, model-economics, and a registry-driven…

Native Claude text, Mermaid diagrams, inline images, paste previews and optional Markdown themes

Prévia da cena do Blender no Claude Code e checagem de GLB contra os orçamentos do jogo

A pane beside the session that Claude talks to you through: the task, what it is doing, the notes it files, the questions it went on without, and…

A monster-battle layer for your coding sessions: failing tests become wild bugs, fixes earn XP, and regression tests catch them for your Bugdex

Brings back /buddy: the small creature that watched you code, above the prompt again

A RollerCoaster Tycoon-style park that Claude builds while it works: tool calls lay track, coasters get test runs, crowds pour in, and parks compete…

Review design specs and implementation plans in a pane: move by block, pin comments, ask side questions, submit one review

An always-on companion for Claude Code, after OpenAI's dots: a named avatar that keeps standing responsibilities, runs them on schedules in the…