By yasyf
Review the code Claude just wrote in a PR-like web UI before it commits — comments stream back into the session so Claude can ask questions, and edits are blocked until you press Submit.
Local code-review daemon + Claude plugin — review what Claude writes in a PR-like web UI and stream feedback back.
cc-review lets you review the code Claude just wrote in a GitHub-PR-style web page
before it commits to changes: you leave inline comments, Claude answers your
questions and proposes options right under each comment in realtime, and only once
you press Submit does Claude proceed. Every review and the full back-and-forth is
kept forever in a local SQLite, and re-running /review:start resumes the same review
against your latest changes.
cc-review is a Claude Code plugin that ships a prebuilt cc-review binary (the CLI +
lazily-started local daemon). Add the marketplace and install the plugin:
/plugin marketplace add yasyf/cc-review
/plugin install review@cc-review
In any git repo with uncommitted changes Claude just made, run:
/review:start
Claude prints a http://127.0.0.1:<port>/s/<id> URL. Open it to see a PR-style diff of
the working tree, leave inline comments, and watch Claude reply with questions and
options under each one. Press Submit at the top when you're done — Claude reads the
frozen feedback, asks any leftover questions inline, and then makes the changes. Run
/review:start again after those changes to resume the review against the new diff.
PreToolUse hook hard-blocks
edits until you submit.127.0.0.1; no cloud, no account, no server to keep running.PolyForm-Noncommercial-1.0.0. See LICENSE.
Modifies files
Hook triggers on file write and edit operations
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.
Detect and fix LLM-generated prose tells via the slop-cop CLI. Ships a self-review skill for the agent and bootstraps the binary on first use.
Run the slop-cop CLI on a file (or stdin) to detect LLM-generated prose tells, and report the violations. Bootstraps the prebuilt binary into the plugin's persistent data dir on session start.
Create or non-destructively refresh a fancy GitHub profile README (the <username>/<username> repo) from real data — repos, stars, languages, releases, recent activity — with marker-delimited sections kept fresh by a committed cron updater, flattery gates that hide unimpressive numbers, a snake animation, and an opt-in daily Claude refresh that summarizes recent commits and releases into the activity/shipped lines. Requires the gh CLI authenticated with repo + workflow scopes; the AI banner comes from the gen-image plugin.
Generate project images — mascot logos, README banners (dark/light), social cards, arbitrary illustrations — via the OpenAI Images API with local <1MiB compression. Used standalone or by repo-bootstrap and gh-profile.
Maintain a Claude-written summaries sidecar in any repo: a stdlib-only template module (summaries.py — whole-file staleness gate, sanitizing, key matching) that consumer render scripts commit and read, plus a config-driven headless refresh skill that rewrites the sidecar whole from real commit/release data with reuse-before-rewrite and a strict flattery law. Consumers describe their groups, raw-material recipes, and render command in .github/summaries.config.json; the gh-profile plugin is the reference consumer.
npx claudepluginhub yasyf/cc-review --plugin cc-reviewMemory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.