test-runner

Claude Code Plugins Marketplace

Disclaimer

These plugins are just me playing around with Claude Code's plugin system, and have been iteratively developed by prompting Claude Code to improve them each time the behavior didn't match what I had in mind.

There are probably much better-designed plugins that do the same things with more features; if you know of any, please open an issue and I will happily mention them in this README as better alternatives:

• In particular, the safer-git plugin should probably be more generic and not be limited to git commands. Hopefully Anthropic will eventually improve the permission system, but in the meantime, I hope there are better plugins than that one.
• The test-runner plugin also seems like something interesting that has probably been done better by others -- I'd love to know of such alternatives!

A collection of community plugins for Claude Code that enhance safety, monitoring, and developer experience.

Installation

Add this marketplace

/plugin marketplace add clemux/claude-code-plugins

Install plugins

# Install the safer-git plugin
/plugin install safer-git@clemux-claude-code-plugins

# Install the subagent-metrics plugin
/plugin install subagent-metrics@clemux-claude-code-plugins

# Install the commit plugin
/plugin install commit@clemux-claude-code-plugins

# Install the test-runner plugin
/plugin install test-runner@clemux-claude-code-plugins

# Install the worktree plugin
/plugin install worktree@clemux-claude-code-plugins

Available Plugins

safer-git

Blocks dangerous git commands for all agents (main + subagents), preventing accidental data loss and history rewrites. It's called "safer" rather than "safe" because it reduces risk but cannot guarantee complete protection — an LLM agent can find indirect execution paths (scripts, eval, non-Bash runtimes) that bypass command-level hooks. See known bypass vectors and limitations.

Protects against:

• Force pushes (git push --force, --force-with-lease)
• History rewrites (git commit --amend, git rebase -i, git filter-branch)
• Uncommitted work loss (git reset --hard, git checkout ., git clean -f)
• Hook bypasses (git commit --no-verify)
• Stash deletion (git stash drop, git stash clear)
• Alias-based bypasses (git config alias.*)

How it works: Registers a PreToolUse hook on the Bash tool that intercepts commands, splits compound statements, and regex-matches each segment against a blocklist. Denies execution with descriptive error messages when dangerous patterns are detected.

Dependencies: jq, grep -P (PCRE support)

Read more →

subagent-metrics

Logs token usage for every subagent (Task tool) call, enabling cost attribution and skill optimization.

Features:

• Automatic logging to ~/.claude/subagent-metrics.jsonl
• Per-skill cost attribution (when skills tag their Task descriptions)
• Session-level profiling with loaded skill sets
• Model usage breakdown (Haiku vs Sonnet)
• Atomic append with flock for concurrency safety

Log fields: timestamp, session ID, model, subagent type, triggering skill, description, total tokens, duration, loaded skills

How it works: Registers a PostToolUse hook on the Task tool that extracts token usage from result text, parses skill tags from descriptions, and appends structured JSON logs.

Dependencies: jq, flock

Read more →

commit

Smart conventional commits with automatic change analysis and splitting via the /commit command.

Features:

• Analyzes staged and unstaged changes, groups them into logical commits
• Intent-based splitting heuristics with conventional commit messages
• Interactive confirmation before executing (or auto mode to skip)
• Pre-commit hook failure handling (fixes issues, creates new commits)
• Optional push after committing

Usage: /commit, /commit push, /commit auto

How it works: Uses a heavy-skill/thin-subagent architecture — Opus does all analysis, splitting, and planning in the skill, while a dedicated Haiku subagent executes git commands. The custom commit subagent type enables proper attribution in subagent-metrics logs.

Read more →

test-runner

Runs pytest with coverage and baseline tracking via the /tests command.

Features:

• Coverage table with deltas from previous runs
• Coverage trend (last 5 runs)
• Test summary with new failures, fixed tests, and pre-existing failures
• Structured markdown report
• Baseline history stored in .tests-baseline.json

Usage: /tests, /tests tests/test_auth.py, /tests -k "test_login"