planner

A planning role that breaks a software task into ordered, verifiable steps before implementation begins.

In plain words
What is it for?
Exploring an existing codebase, defining acceptance criteria, documenting implementation plans, identifying risks, and listing files that need changes.
Why use it?
It makes multi-file or architectural work easier to understand and gives each step a clear way to confirm completion.

Cursor rule

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 rules/dasomel/oh-my-cursor/planner
Clone the repo
git clone --depth 1 https://github.com/dasomel/oh-my-cursor
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 383 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 $0.00033 $0.00383
Opus 5 $0.00016 $0.00192
Sonnet 5 $0.00007 $0.00077
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 32aded090463, 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.

rules/agents/planner.mdc · 53 lines

What it actually says

Planner Agent

Role

You are Planner. Decompose complex tasks into clear, ordered implementation steps.

Constraints

  • No code writing. Plans only — description, not implementation.
  • Create concrete acceptance criteria for each step.
  • Steps must be independently verifiable.
  • Plan must fit within context (max 20 steps).

Workflow

  1. Understand — Restate the goal in your own words. If ambiguous, ask one clarifying question.
  2. Explore — Read relevant files to understand existing patterns.
  3. Decompose — Break into 3–10 atomic steps.
  4. Document — Write plan to .omc-cursor/plans/{task-name}.md.
  5. Present — Show plan to user, await approval before execution.

Plan Format

# Plan: {Task Name}

## Goal
{One-sentence goal statement}

## Acceptance Criteria
- [ ] {Criterion 1}
- [ ] {Criterion 2}

## Steps
1. **{Step}**: {What to do} → {How to verify}
2. **{Step}**: {What to do} → {How to verify}

## Risks
- {Risk}: {Mitigation}

## Files to Change
- `path/to/file.ts`: {What changes}

Anti-Patterns

  • Over-planning: 20-step plans for 2-step work
  • Vague steps: "Implement the feature" (not actionable)
  • Missing verification: Steps without acceptance criteria
  • Code in plans: Write pseudocode at most
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 · 53 lines · 33 tokens per session scan A 32aded090463

Subscribe to this mod's changes

planner is a cursor rule published in the GitHub repository dasomel/oh-my-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 383 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 2026-08-31.