CC Commander — Master Claude Code instantly. The Fable Method: 12 enforceable gates so any model delivers Fable-shaped results. 71 plugin skills, 22 specialist agents, 23 lifecycle hooks (39 handlers). Free for now. commanderplugin.com
This repository also configures its own agents. See what commander tells them →
Command Claude Code
Spawn, monitor, stop and merge parallel agents in isolated git worktrees through the Composio ao CLI. Use when you want several agents working on one project at once.
Command Claude Code
Answer a quick side question mid-task without editing files or losing the current task, then resume where work paused. Use when you want a fast explanation or second opinion without derailing the work.
Command Claude Code
Audit the current project for dependency vulnerabilities, oversized bundles, type errors, dead code, hardcoded secrets, undocumented env vars and a missing CLAUDE.md. Use when you want a health score before a release or review.
Command Claude Code
Fix build and type errors one at a time with the smallest safe change, re-running the build after each fix. Use when a build, compile or type check is failing.
Command Claude Code
Turn on careful mode for the session: refuse destructive commands, confirm before mutations, show diffs before writes, and keep a command log. Use when working near production data or shared infrastructure.
Command Claude Code
Switch responses to caveman mode at lite, full or ultra intensity to cut output tokens while keeping technical accuracy. Use when iterating fast and you want terse answers.
Command Claude Code
Create, verify, list or clear named workflow checkpoints: a verified git snapshot logged with its SHA, compared later for changed files, tests and build. Use before risky steps and at feature milestones.
Command Claude Code needs its repo
Start NanoClaw, the vendored zero-dependency REPL with persistent markdown sessions, model switching, skill hot-load, branching, search, compaction, export and metrics. Use when you want a lightweight persistent agent session outside the main chat.
Command Claude Code
Open, inspect or start CloudCLI web sessions so Claude Code is reachable from a browser or phone. Use when the user asks for web or mobile access to a running session.
Command Claude Code
Report a delegated task as finished: summary of changes, tests and commits, plus an optional tracker update. Use when a task delegated by an orchestrator or tracker is done.
Command Claude Code
Capture the patterns, corrections and decisions from the work just done into tasks/lessons.md, or review and prune existing lessons. Use after finishing a task or when the user says compound, lessons or retro.
Command Claude Code
Show how full the context window is, which components use the most of it, and when to save the session and compact. Use when the session feels slow, long or near its context limit.
Command Claude Code
Show what agent sessions cost today, yesterday and in total, broken down by day, agent or model, with a daily budget alert. Use when the user asks about spend, token usage or burn rate.
Command Claude Code
Run a structured debug session: gather context, rank hypotheses, test them without editing code, then fix with a regression test and record the lesson. Use when a bug's cause is unclear.
Command Claude Code
Plan a project into dependent missions and run parallel Claude Code agents in isolated worktrees through the DevFleet MCP server, then read each mission's report. Use when the user wants DevFleet orchestration.
Command Claude Code
Answer a library, framework or API question from its current documentation via Context7, with code snippets. Use when the user asks how to use a library or wants docs newer than training data.
Command Claude Code
Define, run, and report evals for a feature before and during implementation, tracking capability and regression pass rates in .claude/evals/. Use when starting eval-driven development or checking whether a feature is ready to ship.
Command Claude Code
Kick off a feature: research context, create an isolated branch, confirm a green baseline, write a task breakdown, and the first failing test. Use when starting new feature work in a git repository.
Command Claude Code
Fork the current work into isolated git worktrees to try several approaches side by side, compare them on measured results, and merge the winner. Use when choosing between implementations, attempting a risky refactor, or testing competing bug theories.
Command Claude Code
Run the deterministic harness audit and return a prioritized scorecard of the project's Claude Code setup: tools, context, quality gates, memory, evals, security, cost. Use when checking setup health or deciding what to harden next.
Command Claude Code
Audit the slash command library: inventory every command, grade quality, find missing categories, and apply approved updates, additions, and archivals. Use when the command library feels stale, duplicated, or incomplete.
Command Claude Code needs its repo
Run the continuous-improvement pipeline: scan GitHub and npm for new Claude Code tooling, score proposals, and approve or reject them in a local queue. Use when reviewing ecosystem findings or deciding what to adopt next.
Command Claude Code
Scaffold or refresh a project's CLAUDE.md, tasks/, lessons.md and .claude/settings.json from the CC Commander template, preserving custom sections. Use when starting a project or when CLAUDE.md is missing, stale, or behind the template.
Command Claude Code
Extract a reusable pattern from the session, run a quality gate against existing skills and memory, choose global or project scope, and save it as a skill only after your OK. Use when a session solved something worth keeping and you want it checked before it is saved.
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: