Select Coder — AI skill for Claude Code
Recommend which coder agent and model should execute a coding task — probes locally available backends (opus, codex, agy, devin) once into a cached config, scores the task against a capability matrix.
How to install Select Coder
Installs to ~/.claude/skills/bestdan-workflow-skills-select-coder/SKILL.md
mkdir -p ~/.claude/skills/bestdan-workflow-skills-select-coder && curl -fsSL https://raw.githubusercontent.com/bestdan/workflow-skills/HEAD/commands/select-coder.md -o ~/.claude/skills/bestdan-workflow-skills-select-coder/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Select Coder does
description: Recommend which coder agent and model should execute a coding task — probes locally available backends (opus, codex, agy, devin) once into a cached config, scores the task against a capability matrix (correctness, speed, cost, context, creativity, autonomy, verification, secret exposure, containment), and returns ranked coder specs; usable standalone or as orchestrate-coders --coder arguments allowed-tools: Bash, Glob, Grep, Read, Write, Edit, WebSearch, WebFetch, AskUserQuestio
Alternatives in AI
- Qwen Code — A command-line AI workflow tool adapted from Gemini CLI, optimized for Qwen3-Coder models with enhanced parser 20.8k ★
- Sast Skills — Collection of agent skills that turn your AI coder into a SAST scanner 620 ★
- Designing AI Agents — Companion code for 'Designing AI Agents' (Manning, 2027) — 27 agent design patterns, organized by the 7 cognit 181 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Refresh Coder Comparison
Re-research the coder capability matrix — re-check benchmark boards, pricing, model rosters, safety evaluation
Zommi
Open-source desktop companion for AI agents. Select and annotate screen regions, then share screenshots and av
Herdr Agent Usage
Credential-scoped AI quota, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin
GitHub Demand Radar
AI Agent Skill to scan GitHub issues/PRs with JTBD + RICE scoring, find high-value market gaps, and generate f
Universal Debug Mode Skill
Evidence-driven debugging skill for AI agents: generate competing hypotheses, instrument with isolated runtime
LLM Monopoly
Autonomous Generative Answer Engine Probing & Competitive Displacement Mesh. Continuously probes Perplexity, C
Related Agents
Connect
Detect and configure WordPress site access. Probes for available connection methods and helps the user set up
Osf Gap Audit
Requirements gap audit worker. Extracts a capability checklist from a spec file or list, inventories the codeb
Lead Consistency
Cross-unit consistency pass and deduction-matrix arbitration for an audit-style evaluation run. Runs ONCE per