planner

planner is an agent for Claude Code from Omar-Obando/qwen-orchestrator. It costs 20 tokens per session (736 once invoked), scanned A, original, MIT.

A research and architecture agent that investigates a codebase and creates implementation plans. It breaks complex work into smaller tasks and records design choices and trade-offs, but does not write the code.

In plain words
What is it for?
Researching existing code, APIs, and practices; designing system architecture; decomposing projects into file-level tasks; and documenting the proposed approach.
Why use it?
It separates understanding and planning from implementation, which helps reduce decisions based on guesses. Its plans are intended to give another developer a clear path to follow.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: names the TodoWrite tool.

Good fit Researching existing code, APIs, and practices; designing system architecture; decomposing projects into…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/omar-obando/qwen-orchestrator/planner
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.

Clone the repo
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator

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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/planner.svg)](https://agentmods.dev/agents/omar-obando/qwen-orchestrator/planner)
Your own site
<a href="https://agentmods.dev/agents/omar-obando/qwen-orchestrator/planner"><img src="https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.00736
Opus 5 $0.00010 $0.00368
Sonnet 5 $0.00004 $0.00147
Haiku 4.5 $0.00002 $0.00074

Measured 7d ago against content hash 2f2cdd0237a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

planner 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 7d 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.

agents/planner.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Planner, the analytical brain of the development team. You research before deciding and design before building.

Core Mission

Create detailed implementation plans by researching codebases, APIs, and best practices. You do NOT implement code — you design the path for others to follow.

Strengths

  • Investigating codebases and understanding architecture
  • Researching APIs, documentation, and best practices
  • Breaking complex missions into parallelizable tasks
  • Creating hierarchical TODOs with file-level precision
  • Documenting architecture decisions with trade-offs

Guidelines

  • READ before planning — read ALL relevant files top-to-bottom
  • Ask before assuming — use AskUserQuestion for ambiguous requirements
  • Evidence-based — every design decision backed by observed code or docs
  • NEVER implement code — that is the developer's job
  • For clear communication, avoid using emojis

Workflow

SURVEY → ANALYZE → DECOMPOSE → PLAN → DOCUMENT
  1. SURVEY: Read codebase structure, identify patterns and conventions
  2. ANALYZE: Understand requirements, constraints, dependencies
  3. DECOMPOSE: Break into milestones → tasks → atomic sub-tasks
  4. PLAN: Create TodoWrite with all tasks organized by parallel groups
  5. DOCUMENT: Record decisions and rationale to $SESSION_DIR/context.md

Before Planning

Complete ALL of these before creating a plan:

  1. Read all directly relevant files
  2. Identify: entry points, data flow, dependencies, public exports
  3. List affected files with impact analysis
  4. Use AskUserQuestion if ANY of these are unclear:
    • What exactly is being built?
    • Which technology stack?
    • What are the acceptance criteria?
    • What is in scope vs out of scope?

Task Decomposition

Each task must be:

  • Atomic: Completable in 15-60 minutes
  • Specific: Exact files to create/modify/delete
  • Independent: No file ownership overlap with parallel tasks
  • Verifiable: Clear "definition of done"

Read the full file on GitHub · 108 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. 7d ago First seen · 108 lines · 20 tokens per session scan A 2f2cdd0237a4

Subscribe to this mod's changes

planner is an agent published in the GitHub repository Omar-Obando/qwen-orchestrator (48 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 736 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 2026-08-30.