Claude Code Code Review and Testing Mods

Contemporaneous R&D time and AI-usage ledger: engagement hours by business component, list-price usage estimates, a weekly review with buttons, a CPA…

A shared task tracker for agents and people working in one repository: claim tasks, declare the files you touch, get refused on overlaps, review

Adds a TLDR button that summarizes Claude's latest response in a side pane

Automatic effort and model, and a quota that limits how many agents run, not how well one runs

A fox spirit that lives on your work: passing tests feed it, finished turns cheer it, it plays while you are quiet, and it grows up to nine tails

Runs your project's own linter fix (eslint, ruff or golangci-lint) on each file Claude writes or edits, only when the project has that linter's…

Routes heavy Bash commands (test suites, builds, Docker) to a second machine over ssh, with the PATH export and working directory already right, and…

See images in the terminal: thumbnails of what you paste above the prompt, and each image Claude reads drawn under its row in the transcript

Docs worth keeping: docs-review asks Haiku whether new text will be read again, docs-no-repeat-code flags lines that may restate code, limit-docs…

Shows the Markdown files Claude edits, rendered like GitHub, in a pane next to the chat

Roadmap pane: task stages top to bottom (context → implementation → checks → tests → push → deploy), marked automatically from Claude's actions

One board for what is waiting on you across your projects: sessions waiting for an answer or approval, proposals to review, blockers, action items…

Runs search subagents on Haiku and general-purpose ones on Sonnet, and /orchestrate splits a big task across scout, worker and reviewer subagents

Type ;;ss in a message (or ;;ss3 for three) and your latest screenshots go with it, so you never have to drag them in

Warsztat modów Claude Code: narzędzie modelu `szukaj` (JSDoc i sygnatura zdarzenia, metody `$.…` albo typu z lokalnego claude-code/index.d.ts po…

Scripts worth keeping: scripts-review asks Haiku whether a new script could just be typed again when needed

Holds `gh pr merge` until CI passes and one Codex review (OpenAI's luna model) has run

The fix must make a test fail first: reverts your source changes, runs the changed tests and requires a failure, restores (verified by hash) and…

Progress bar above the prompt and an agents panel (/agents-info): running, finished and planned subagents with model, progress, context, cost and…

SDD capability 03: the sole phase/prompt interceptor and human approval gate before a Spec-Kit phase runs

Tablero de PRs abiertos, checks, reviews y worktrees, con atajos para pedirle cosas a Claude

Shows repo@branch and its listening ports in the hint line under the prompt, and a /worktrees pane to review and clear finished worktrees

A quick second pair of eyes after edits: reviews the turn's diff in the background and offers to fix what it finds

Makes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standing orders and second-opinion reviews…

Tests worth keeping: static-text asks Haiku whether the text assertions a UI test gains only retype copy its component always shows

Runs the project's checks from a band button, and before Claude's git commit, and hands back only the failures

Counts the distinct files a turn edits and stops at a threshold to make the goal get restated, so a small ask cannot quietly become a refactor

Claude Code mod from cpeaustriajc/cj-stack

Know whether your auto-memory index loaded whole

Your open pull requests in a Dracula-themed pane: CI, Codex review and whether each one already reached your integration branch, plus a chip above…

Finds AI slop in Claude's changes (dashes, comment blocks, comments that repeat the code, tests that assert nothing, filler phrases) and tells Claude…

Stops before Claude writes API keys, tokens, private keys or a non-ignored .env into files, git add or commits

/prs: your open PRs across your repos with Vercel preview links, checks, merge state and worktree

/promote previews merging the current branch into an integration branch (staging, homolog, develop); /promote go does a full merge in a temporary…

Per-prompt snapshots of your whole project, so you can preview and restore to any earlier prompt, Bash changes included

Shows which machine and repo a session runs in (Mac or the claude-code container, repo, branch, fork) in the status line, and nudges Claude when it…

One workspace for watching and understanding Claude's work: a one-line band above the prompt and a pane with Now, Changes (file diffstat, changed…

/second-opinion asks Fable (or the model you set) for a candid senior review of your recent commits, branch, uncommitted diff or a plan file, in the…

Watch PRs outside the model: polls CI, reviews and threads with gh, wakes the session only when something actionable happens, and denies sleep-poll…

In Xcode projects only: one line with the last build and test result and the booted simulator; flags 0-test runs; blocks a second xcodebuild while…

Walk a code review's findings one at a time: the skill asks per finding, the mod draws Finding N/M with a progress bar and the decisions so far

Shows test runs in a pane

Finds the commit that broke something: git bisect with your test command in a temporary worktree (your working tree is never touched), live progress…

Run the project's tests after any turn that edited files, print pass or fail under Claude's answer, and send the failure back to Claude with one /fix…

The repo's inbox/ work queue as a pane: todo items at the root, then processing/, review/, done/ and blocked/

Reusable prompts one command away: /snip review drops your saved review prompt into the prompt box, with {{selection}}, {{branch}}, {{date}} and…

Two short questions about Claude's latest code change, answers one press away

A pane showing git diff --stat and the untracked file count, refreshed after each turn