Standard Worker High — Development agent for Claude Code
Default execution tier — most feature work, bug fixes, and moderate multi-file refactors that follow established patterns.
How to install Standard Worker High
Installs to ~/.claude/agents/tammai-bigin-skills-standard-worker-high.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/tammai/bigin-skills/HEAD/agents/standard-worker-high.md -o ~/.claude/agents/tammai-bigin-skills-standard-worker-high.md Restart Claude Code, or start a new session, for it to be picked up.
What Standard Worker High does
name: standard-worker-high description: Default execution tier — most feature work, bug fixes, and moderate multi-file refactors that follow established patterns. Spawned by model-router for tasks scoring 2-4 on its capability rubric. model: opus effort: high skills:
- debug-workflow
- write-tests
You were routed here by `model-router` because the task scored 2-4 on its capability rubric: an established pattern needing real adaptation, or some ambiguity to resolve, or enough files t
Alternatives in Development
- Gsd Dom Verifier — Verifies live-DOM acceptance criteria for a completed execution wave using a browser MCP server 8.8k ★
- Retool Fidelity Review — The fourth review for a Retool migration slice — walks the export query by query and asks whether each behavio 7.2k ★
- Scope Guard (Shared Prompt Block For Tier 2 Agents) — This file is not a standalone agent 213 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Standard Worker
Default execution tier — most feature work, bug fixes, and moderate multi-file refactors that follow establish
Default Worker
Main implementation worker (Sonnet). Use for normal, well-specified coding work — features, edits, refactors,
Exec Standard
MID tier at medium effort. Execution agent for well-bounded implementation in an isolated git worktree - new s
Router Opus
Worker subagent dispatched by the auto-model-router for deep work — architectural refactors, multi-file cross-
Mathodology Award Judge
Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria.
Blind Evaluator
Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the impl
Related Skills
Adding New Preset
Use when adding a new preset screening strategy to the MCP server. Ensures presets follow established patterns
Terminal Dx
You are designing or improving a terminal-facing UI for the Syn137 project. Follow these patterns exactly. The
Prompt Architecture
Reference guide for designing production LLM prompt systems in this codebase. Covers the Two-Pass Gap Analysis