St Worker Medium — Project Management agent for Claude Code
Strikethroo task-execution worker at the MEDIUM reasoning-effort tier.
How to install St Worker Medium
Installs to ~/.claude/agents/lullabot-sandbar-st-worker-medium.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Lullabot/sandbar/HEAD/.claude/agents/st-worker-medium.md -o ~/.claude/agents/lullabot-sandbar-st-worker-medium.md Restart Claude Code, or start a new session, for it to be picked up.
What St Worker Medium does
name: st-worker-medium description: Strikethroo task-execution worker at the MEDIUM reasoning-effort tier. The default executor for standard, single-domain implementation tasks with straightforward logic. Effort is fixed by this agent's frontmatter; the orchestrator overrides the model per task. model: sonnet effort: medium
You are a Strikethroo task-execution worker. An orchestrator dispatches you to implement exactly one task from a Strikethroo plan.
Operating rules
- **Pre-flig
Alternatives in Project Management
- Code By Agents — Orchestration framework for designing and coordinating Claude Code agents with sophisticated orchestration log 812 ★
- Team Worker — Unified worker agent for team pipelines 530 ★
- Fire Project Researcher — Researches a specific domain focus area for new project/milestone initialization 77 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
St Worker High
Strikethroo task-execution worker at the HIGH reasoning-effort tier. For complex tasks with non-trivial logic,
Sonnet Executor
Executes a single MEDIUM-effort task from the planner (multi-file change, new component, logic implementation)
St Worker Low
Strikethroo task-execution worker at the LOW reasoning-effort tier. Dispatched by the Strikethroo executors fo
Javis Worker
Executor agent for the agent-javis skill. Low effort by default — understands the relevant code, does the task
Miner Medium
Delegate worker pinned to MEDIUM reasoning effort. Calibrated for C-coding since the 2026-07-07 refit (the C6
Effort Grader
Blind grader for effortmining. Grades one artifact against a task prompt and a fixed rubric ONLY. The input pa
Related Skills
The Council
Three-tier AI agent MCP orchestration system: Chancellor (Opus), Executor (Sonnet), Aide (Haiku)
Public Browser
Token-efficient Chrome browser automation MCP server for AI agents. Direct CDP, a11y-tree refs, multi-tab, ser
Which Model
Which model actually answered your coding agent, from your own machine: Claude Code and Codex transcripts read