Cm — Productivity skill for Claude Code
Run Codemium on a coding task with optional fast, deep, or critical engineering depth.
How to install Cm
Installs to ~/.claude/skills/ahfaruq-codemium-cm/SKILL.md
mkdir -p ~/.claude/skills/ahfaruq-codemium-cm && curl -fsSL https://raw.githubusercontent.com/ahfaruq/codemium/HEAD/commands/cm.md -o ~/.claude/skills/ahfaruq-codemium-cm/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Cm does
name: cm description: Run Codemium on a coding task with optional fast, deep, or critical engineering depth. argument-hint: "[fast|deep|critical] "
Use the `cm` Codemium skill for the following request:
$ARGUMENTS
Interpret a leading `fast`, `deep`, or `critical` as the requested engineering-depth override. Otherwise use automatic depth. Apply the safety floor, shared `.codemium/` Project Brain, bounded working set, smallest justified change, risk-aware verification, scop
Alternatives in Productivity
- Build In Public — Build-in-Public — generate posts from your engineering work, anonymize, and schedule via Buffer 705 ★
- Agentacct — See what your coding agents did and what it cost 665 ★
- MCP Tree-sitter Server Roadmap — This document outlines the planned improvements and future features for the MCP Tree-sitter Server project 288 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Verify Loop Skill
A Claude skill that runs a supervised, self-verifying loop on a coding task. The loop is the easy part — verif
Paceflow
Deterministic workflow enforcement and persistent engineering memory for long-running coding agents.
Dependency Mapper
Map project and task dependencies with critical path analysis and circular dependency detection
Meridian
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
Agenfk Deep
Run a task using full Multi-Agent Orchestration (Deep Mode)
Crew History
View CodeCrew task history with optional filters. Supports --type, --agent, and --limit flags.
Related Agents
Socratic Questioner
Mandatory pre-implementation interrogation. Use before any non-trivial coding task to surface assumptions, fin
Questioner
Mandatory pre-implementation interrogation. Use before any non-trivial coding task to surface assumptions, fin
Spider Man
Fast implementer that writes production code, runs builds, creates tests, and fixes bugs. Use for any coding o