Custom hooks, skills, and rules for Claude Code: adds automatic Python formatting, context persistence across sessions, parallel subagent workflows, and a status line.
This repository also configures its own agents. See what claude_extensions tells them →
Skill Claude Code
Reviews code for design, correctness, performance, and test quality. Use when the user wants a code review of files, a diff or PR, or the whole project before shipping or merging.
Skill Claude Code
Delivers structured, adversarial feedback on a plan or design document, surfacing risks and gaps before implementation. Use when the user wants a plan or document reviewed.
Skill Claude Code
Implements the next batch of an existing plan, orchestrating subagents with test and lint validation. Use when the user wants to build a plan's next batch.
Skill Claude CodeCodex
Checkpoints session progress to status tracking files. Use to save state mid-session, after a major task, before ending, or when nearing context limits.
Skill Claude Code
Audits code for security vulnerabilities — injection, auth and access control, crypto, secrets, SSRF, and insecure configuration. Use when the user wants a security review of the codebase, a file or directory, or a diff before shipping, or when changes touch auth, input handling, or external integrations.
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: