Claude Code Code Review and Testing Mods

Marks your uni assessments against the real rubric with High Distinction as the bar: a strict nine-section review, re-marks that catch regressions, a…

Starts breadcrumbs' manual-test testers the moment you press Start, without going through the main agent

Keep a resettable side conversation with the latest main-session context in a sidebar tab

Verifiche: i test veloci a fine risposta e la CI su GitHub, in un pannello e nella riga di stato

Runs Pint and Larastan after Claude edits PHP, and Pest or PHPUnit on demand, then shows the results in a live pane and the status line

Plan C test: ask Claude to pin a short checklist above the prompt

Reviews unpushed commits against REVIEW_GUIDELINES.md before Claude runs git push

Claude says the tests pass

The review gate as a tool.check function hook

Toolbox for Claude Code's Workflow tool — author deterministic multi-agent workflow scripts (workflow-composer, with the @workflow-toolbox…

No claims without evidence: flags "tests pass", "CI green" and "verified" claims that nothing in the turn backs up

Stamps recorded pr-review decisions (RESOLVED, CLOSED_NO_ACTION) into the bubble memo, PR_<N>_Bubbles.md

Replies that point at code: ask with /code-reference (a question, or a PR to review) and each place the reply names opens in a code pane beside it…

/codex-loop <PR> hands Claude a review loop with the Codex GitHub bot: request a review, weigh each finding, fix or 👎 it, reply, resolve and repeat…

Blocks commits without [TICKET] when the branch has a ticket, and commits that only fix linting or formatting; suggests the correct message

Automatic compaction summarizes only the older part of the conversation and keeps the latest part word for word; a reopen tool brings back anything…

A hand_off tool: Claude gives a self-contained task to a cheaper worker model (Haiku for lookups and mechanical changes, Sonnet for build work) that…

Context Diet: trims huge tool outputs (build logs, long test runs, big fetches) before they reach the context, keeps the full text on disk, and shows…

GitHub pull requests in Claude Code: an inline card (/pr), a PR bar above the prompt (/pr-band), checks, reviews, unresolved threads and Fix with…

Switches a session into an agentic development loop: a PM main thread that plans tickets and dispatches dev and review agents

Previews pasted images and images Claude sends, with Open and Reveal buttons (Explorer on WSL/Windows, Finder on macOS)

/image-preview opens a pane listing every image of the session, pasted or returned by a tool, and shows the one you pick

Pasted images become chips you can click to open in the system viewer, in the transcript and above the prompt

Review markdown files line by line, leaving <!-- REVIEW --> comments in the file

Type /mods to preview the workflow mods, tick the ones you want and install them

Draft and apply mod settings, with declared presets, undo and observed hook previews

POWERTRAY: a pane of things to look at or listen to (what Claude made this session, things related to what you are on, local servers), a player for a…

Put ++ at the start or end of a prompt to have it rewritten into a clear prompt for review before sending

A rail of your prompts above the input (hover to preview, click to jump), a dock beside the transcript, and quote-reply from any selected text

Reviews how you ran the whole session, not one prompt: a 1 to 100 score on a red-to-green gauge, what went well, what to do differently, and the…

🚢 One press raises a PR for the session's work, then watches CI and reviews and works through the feedback until it's ready to merge

Fascia sopra il prompt: ramo e stato git, worktree della chat, esito delle review, modello, contesto, effort, limiti, costo e skill; nell'app a tre…

A TODO.md task board (Todo / Doing / Review / Done) with a side panel: quick capture, Claude enrichment with IDs, reviews and done logs

Multi-line status HUD above the prompt over data families (hooks/data/*.ts pure collectors, one core subscription per event), with the…

Quality-first routing: picks main-loop effort (medium to max) per request, assigns model and effort to subagents by kind and weight, checks Workflow…

Every look you reject becomes a rule for that project, with your screenshot, so Claude never brings it back; it also says when Claude changed UI…

Windows only: a small floating strip over Windows Terminal that previews each [Image #N] you paste or drop, until you send

Previews pasted images in colour: above the prompt while drafting, and under the message in the transcript

Puts tsc, linter and secret-scan diagnostics in the result of every Edit and Write, so Claude fixes what it broke in the same turn

Antes do Claude commitar ou enviar: bloqueia segredos (GitHub, AWS, OpenAI, Anthropic, Brevo, Bitrix24, Meta…), arquivos de segredo, conflitos e…

A checklist pane for manual testing: Claude publishes the steps, you mark each pass, fail or skip with a note, and the results go back as one message

A row above the prompt with live status of xvendor (xv) cross-vendor jobs: one line per running job or job finished in the last 10 minutes (vendor…

A second player reviews before the PR: gh pr create waits for a second-model review of the branch diff, and a failing review with a high finding…

A Tamagotchi-style coding companion: it earns XP from edits, reads, passing tests and commits, levels up and evolves, and needs feeding, play and…

Adds a Diagram button that draws the flow or architecture from Claude's latest response in its own pane tab, saved as SVG and draw.io

A pane for finding and reading files without asking the model: an explorer with search by name that lights up the files Claude reads, writes and…

Keeps git history tidy: commit messages in Conventional Commits with no Claude credit, then a Haiku review of the body; an MR whose branch lacks the…

Development standards: look before building, test what changed, pass the repo's checks, keep the rules in view