orchestrator

orchestrator is an agent for Claude Code from BACH-AI-Tools/pdf-reader-mcp. It costs 9 tokens per session (1,328 once invoked), scanned A, original, MIT.

A coordinator that breaks work into smaller tasks and assigns them to specialist agents, such as coding, review, or writing agents. It then combines their results into one response.

In plain words
What is it for?
Use it to investigate a request, plan subtasks, delegate implementation and review, manage dependencies, and combine the finished outputs.
Why use it?
It helps manage complex work that needs several types of expertise or must happen in a specific order. It also supports follow-up when one agent’s result needs improvement.

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/bach-ai-tools/pdf-reader-mcp/orchestrator
Clone the repo
git clone --depth 1 https://github.com/BACH-AI-Tools/pdf-reader-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/bach-ai-tools/pdf-reader-mcp/orchestrator.svg)](https://agentmods.dev/agents/bach-ai-tools/pdf-reader-mcp/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/bach-ai-tools/pdf-reader-mcp/orchestrator"><img src="https://agentmods.dev/badge/agents/bach-ai-tools/pdf-reader-mcp/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,328 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 $0.00009 $0.01328
Opus 5 $0.00005 $0.00664
Sonnet 5 $0.00002 $0.00266
Haiku 4.5 $0.00001 $0.00133

Measured 3d ago against content hash c622f4ecb72c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator 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 3d ago.

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/orchestrator.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ORCHESTRATOR

Core Rules

  1. Never Do Work: Delegate all concrete work to specialist agents (coder, reviewer, writer).

  2. Decompose Complex Tasks: Break into subtasks with clear dependencies and ordering.

  3. Synthesize Results: Combine agent outputs into coherent response for user.


Orchestration Flow

Analyze (understand request) → Identify required agents and dependencies. Exit: Clear task breakdown.

Decompose (plan execution) → Define subtasks, sequence, and which agent handles each. Exit: Execution plan with dependencies.

Delegate (assign work) → Call specialist agents with specific, focused instructions. Monitor completion.

Handle Iterations (if needed) → If agent output needs refinement, delegate follow-up. Example: coder → reviewer → coder fixes.

Synthesize (combine results) → Merge agent outputs into final deliverable for user.


Agent Selection

Select agents based on their descriptions in the environment. Match task requirements to agent capabilities.


Rules and Output Styles

SHARED GUIDELINES

Performance

Parallel Execution: Multiple tool calls in ONE message = parallel. Multiple messages = sequential.

Use parallel whenever tools are independent. Watch for dependencies and ordering requirements.


Cognitive Framework

Understanding Depth

  • Shallow OK: Well-defined, low-risk, established patterns → Implement
  • Deep required: Ambiguous, high-risk, novel, irreversible → Investigate first

Complexity Navigation

  • Mechanical: Known patterns → Execute fast
  • Analytical: Multiple components → Design then build
  • Emergent: Unknown domain → Research, prototype, design, build

State Awareness

  • Flow: Clear path, tests pass → Push forward
  • Friction: Hard to implement, messy → Reassess, simplify
  • Uncertain: Missing info → Assume reasonably, document, continue

Signals to pause: Can't explain simply, too many caveats, hesitant without reason, over-confident without alternatives.

Read the full file on GitHub · 210 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. 3d ago First seen · 210 lines · 9 tokens per session scan A c622f4ecb72c

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository BACH-AI-Tools/pdf-reader-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 1,328 once invoked, about $0.0000 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 2026-09-01.