Implementer Medium — Project Management agent for Claude Code
orchestra:implementer at medium effort.
How to install Implementer Medium
Installs to ~/.claude/agents/lsy041015-orchestra-implementer-medium.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/lsy041015/orchestra/HEAD/agents/implementer-medium.md -o ~/.claude/agents/lsy041015-orchestra-implementer-medium.md Restart Claude Code, or start a new session, for it to be picked up.
What Implementer Medium does
name: implementer-medium description: orchestra:implementer at medium effort. Use only when an Orchestra skill dispatches a simple pre-planned task with a brief. model: sonnet effort: medium disallowedTools: Agent
You are the Orchestra implementation worker. The main session owns planning, review, re-review, diagnosis and integration; you implement exactly one bounded task from the brief you are given.
- Read the brief first. Inspect affected source before editing.
- Edit only the allo
Alternatives in Project Management
- Workflow Collab Planner — Collaborative planner working within pre-allocated task ID ranges 530 ★
- Code Review Coordinator — Code review coordinator 63 ★
- Loom Advisor — Read-only advisory agent for debugging and repeated failures 53 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Implementer Xhigh
orchestra:implementer at xhigh effort. Use only when an Orchestra skill dispatches a hard pre-planned task wit
St Worker Low
Strikethroo task-execution worker at the LOW reasoning-effort tier. Dispatched by the Strikethroo executors fo
Tm Implementer
Implements exactly one planned task inside its own git worktree, restricted to a declared file set, and return
Decision Pre Mortem
Pre-mortem analysis of a planned decision or project -- imagines failure, traces failure modes to root causes,
Verifier Medium
Independently audits a diff against an approved PLAN.md — never against the implementer's own summary of what
Miner Medium
Delegate worker pinned to MEDIUM reasoning effort. Calibrated for C-coding since the 2026-07-07 refit (the C6
Related Skills
ExecuteTask
Phase 6 — implement tasks in order, choosing the loop (core / red-green-refactor / prompt-iteration) per task;
Lowkey Effort
An AI skill that auto-calibrates response depth based on task complexity — so you stop burning tokens on simpl
Goal Swarm
Fan out ALL the DTD-declared agents (or an agents= subset) on one thing at once — a workflow when the harness