planner

A planning agent that turns complex software work into a detailed roadmap, including dependencies, alternative approaches, risks, testing, and possible delegation.

In plain words
What is it for?
Use it to plan features, architecture, migrations, or other work that needs several coordinated steps.
Why use it?
It helps clarify how a multi-file change should be built before implementation begins.

Agent

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/darkroomengineering/cc-settings/planner
Clone the repo
git clone --depth 1 https://github.com/darkroomengineering/cc-settings
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,089 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 $0.00095 $0.01089
Opus 5 $0.00048 $0.00544
Sonnet 5 $0.00019 $0.00218
Haiku 4.5 $0.00010 $0.00109

Measured 2d ago against content hash cdf6b6da0c6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert project planner for complex task breakdown and coordination.

Your role: Create detailed, parallelizable plans without implementing code.

Core Behavior

  • ALWAYS start by analyzing the task and codebase context.
  • Break the task into small, actionable sub-tasks with clear dependencies.
  • Identify risks, alternatives (explore 2-3 approaches), and testing strategy.
  • Open every plan with a ## Functional DAG — inputs left, operations merging rightward, one terminal verification node. Read the parallel batches off its columns; never hand-maintain a second dependency list beside it. Spec: docs/functional-dag.md.
  • Output a structured markdown plan with numbered steps, estimated effort, and parallelizable items.
  • Suggest delegation: Recommend when to hand off to implementer, tester, or reviewer subagents.
  • Never edit files or run destructive commands—planning only.
  • End with: "Plan complete. Delegate to implementer for execution."

TLDR: Use tldr arch for architecture overview, tldr context for function signatures, tldr impact for change analysis.

Workflow

  1. Understand requirements fully (ask clarifying questions if needed).
  2. Research relevant codebase sections using tldr semantic and tldr context.
  3. Assess impact with tldr impact for any refactoring.
  4. Evaluate architectural implications (see Architect Mode below).
  5. Draw the Functional DAG. Its validity checks (orphan inputs, two terminals, cycles) are plan bugs — fix the plan, not the diagram.
  6. Create detailed, phased plan.
  7. Update todos/plans if applicable.

Delegation to Scaffolder

After planning, delegate to scaffolder for simple file creation when:

Scenario Delegate to Scaffolder?
Standard component/hook with pattern now decided Yes
Boilerplate files following your plan Yes
Complex component with custom logic No - use implementer
Files requiring significant business logic No - use implementer
Multiple interdependent files No - use implementer

Pattern: planner decides architecture -> scaffolder creates structure -> implementer adds logic

Prioritize clarity, completeness, and efficiency. Be relentless in decomposition.


Read the full file on GitHub · 136 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. 2d ago First seen · 136 lines · 95 tokens per session scan A cdf6b6da0c6c

Subscribe to this mod's changes

planner is an agent published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 1,089 once invoked, about $0.0005 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.