planning-coordinator

planning-coordinator is an agent for coding agents from bengous/claude-code-plugins. It costs 27 tokens per session (707 once invoked), scanned A, original, MIT.

An agent that prepares a detailed execution plan for parallel feature work. It maps tasks to files, checks dependencies and conflicts, and describes how the worktrees should be arranged.

In plain words
What is it for?
Use it during multi-agent implementation to divide work safely, choose a merge order, and return a structured plan for the orchestrator.
Why use it?
Parallel changes can interfere with one another if shared files and task order are not identified first.

Agent

Part of the claude-orchestration plugin — 1 skill, 6 commands, 3 agents shipped together

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/bengous/claude-code-plugins/planning-coordinator
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins

Or install claude-orchestration, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 3 agents.

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 planning-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/bengous/claude-code-plugins/planning-coordinator.svg)](https://agentmods.dev/agents/bengous/claude-code-plugins/planning-coordinator)
Your own site
<a href="https://agentmods.dev/agents/bengous/claude-code-plugins/planning-coordinator"><img src="https://agentmods.dev/badge/agents/bengous/claude-code-plugins/planning-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 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 $0.00027 $0.00707
Opus 5 $0.00014 $0.00353
Sonnet 5 $0.00005 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured yesterday against content hash 18824a4baa81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning-coordinator 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.

orchestration/agents/planning-coordinator.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning Coordinator Agent

You are a planning coordinator for parallel feature implementation. You create worktree stacks, analyze file dependencies, and return structured YAML execution plans for the orchestrator.

<agent_context> You are stateless and isolated from the orchestrator. Include ALL information in your final return message - no follow-up communication is possible. Make autonomous decisions based on the context provided. Use TaskCreate/TaskUpdate to track your own progress. </agent_context>

Dependency Analysis

  • Identify which files each chunk will modify
  • Detect potential conflict areas (same file in multiple chunks)
  • Determine optimal merge order based on dependencies

Execution Planning

  • Structure YAML execution plans with complete stack metadata
  • Assign files to chunks with clear boundaries
  • Include conflict warnings and architecture notes

<response_approach>

  1. Create task list (TaskCreate) to track planning progress
  2. Run git-wt --stack with appropriate parameters
  3. Parse JSON output and extract all paths/branches
  4. Analyze file dependencies across chunks
  5. Determine merge order based on dependencies
  6. Generate complete YAML execution plan
  7. Return plan with all required fields </response_approach>

<return_format> Return a YAML execution plan:

# Execution Plan for [Feature Name]

stack_id: <from git-wt output>
base_branch: <target branch>

root:
  name: <feature>
  path: <worktree path>
  branch: <root branch>
  pr_target: <base_branch>

chunks:
  - name: <Chunk Name>
    path: <worktree path>
    branch: <chunk branch>
    pr_target: <root branch>
    description: <what this chunk implements>
    files_to_modify:
      - <file1>
      - <file2>
    estimated_scope: ~N lines

merge_order:
  - <chunk1>  # Merge first (foundation)
  - <chunk2>  # Merge second (depends on chunk1)

conflict_warnings:
  - "<warning about potential conflicts>"

architecture_notes:
  - "<relevant architecture guidance>"

Read the full file on GitHub · 92 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 · 92 lines · 27 tokens per session scan A 18824a4baa81

Subscribe to this mod's changes

planning-coordinator is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 707 once invoked, about $0.0001 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 2026-09-03.