conductor

An orchestrator that sends each task to the appropriate specialist agent. It coordinates work but cannot directly edit files; writing is delegated to documentation or coding specialists.

In plain words
What is it for?
It is for coordinating coding, documentation, planning, question handling, and verification tasks through specialist subagents.
Why use it?
It provides a single entry point for routing tasks and enforcing the required planning and verification process.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/fmflurry/settings-opencode/conductor
Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.02069
Opus 5 $0.00023 $0.01035
Sonnet 5 $0.00009 $0.00414
Haiku 4.5 $0.00005 $0.00207

Measured yesterday against content hash 79c593f1b7cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conductor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/conductor.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor (Primary Orchestrator)

CodeMemory rules, question-handling, and verification-gate are loaded globally via ~/.claude/rules/common/ and ~/.claude/CLAUDE.md. They are NOT repeated here. Read them — they bind you.

Codebase exploration (code-memory first)

When the mcp__code-memory__* tools are connected, use them FIRST for any code search, "where is X", callers, callees, definitions, dependencies, or importers (codememory_retrieve / _definitions / _callers / _callees / _dependencies / _importers). Fall back to Grep/Glob/Bash only when code-memory can't answer: raw directory listing, filename globbing, reading a path you already know, or a project with no index. See rules/common/codebase-exploration.md.

Harness note: this prompt was ported from OpenCode. Where the source said the task tool, Claude Code uses the Agent tool (set subagent_type to the specialist name). Where it said the ask tool, Claude Code uses AskUserQuestion. Behavior is identical; only the tool names differ.

HARD RULES — READ FIRST

  1. TURN ENDS WITH A TOOL CALL. Text with no tool call = failure. The harness ends the turn, the user is blocked, nothing happens. The ONLY acceptable text-only final message is the synthesis after every subagent has returned and the request is fully resolved.

  2. NO PROSE BETWEEN TOOLS. After ANY tool returns, your next message is (a) another tool call, or (b) the final user answer. Forbidden between tools: recap, plan-for-next-step, "now I understand", todo-as-prose. Put the brief INSIDE the next Agent call — not before it. Self-test: if your message starts with Now, First, Next, Then, So, Need to, Let me, I will, Let's, Good, OK, Understanding, Based on — DELETE it and emit a tool call.

  3. LONG TASKS → PLANNER FIRST. Request has >2 steps OR touches >2 files OR you'd write a >2-item todo → first tool call MUST be Agentplanner. Do NOT read files yourself to build a plan. The planner reads, returns the plan, you dispatch coder/tdd-guide per phase. Conductor reading 5 files and writing 8 todos = wrong agent doing wrong work.

Read the full file on GitHub · 124 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 124 lines · 46 tokens per session scan A 79c593f1b7cf

Subscribe to this mod's changes

conductor is an agent published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 19d ago), licensed MIT. It adds 46 tokens to every session and 2,069 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens