planning

Rules for breaking project work into small, safe slices. Each slice either adds one visible behavior or makes one focused structural change needed for the next behavior.

In plain words
What is it for?
Use it to define focused work units, distinguish user-visible changes from code organization, and keep each step independently reviewable.
Why use it?
It keeps plans understandable and leaves the project in a usable state if work stops partway through.

Cursor rule for Cursor

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/nerds-odd-e/doughnut/planning
Clone the repo
git clone --depth 1 https://github.com/nerds-odd-e/doughnut

Made for: Cursor.

Per session 2,170 This file is loaded in full into every session.
When invoked 2,170 The same file — it is already loaded in full.
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 $0.02170 $0.02170
Opus 5 $0.01085 $0.01085
Sonnet 5 $0.00434 $0.00434
Haiku 4.5 $0.00217 $0.00217

Measured 2d ago against content hash c751f0148430, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning 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.

.cursor/rules/planning.mdc · 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.

Principles for Slice Delivery

Hard rule for every plan (local or GSD): each slice is either Behavior or Structure, stop-safe, and delivers one observable behavior (or one structure change that enables only the immediate next behavior). GSD phase is a roadmap capability (.planning/phases/NN-slug/). Slice grammar is mandatory.

Vocabulary

Term Owner Meaning
Milestone GSD Versioned increment
Phase GSD Roadmap capability. ### Phase N:, .planning/phases/NN-slug/
Plan Shared One PLAN.md (roadmap phase or .planning/quick/)
Slice Local One Behavior or one Structure. Stop-safe wrap-up grain

Behavior and Structure distinction

Behavior (external behavior) has 3 parts: pre-condition, trigger, and post-condition. Each part is:

  • externally observable
  • of user value
  • typically involves state change.

Structure (internal structure) is how code is organized. We want structure to be cohesive, mapped to the domain, and exposing as little information as possible from each module.

Slice principles

Every slice is one of two types:

Type What it does Constraint
Behavior Delivers user value directly observable from the external perspective. Must be externally observable and testable. One observable behavior per slice.
Structure Restructures internals to prepare for the immediate next behavior slice, without changing any external behavior. All changes must be verifiable from the external perspective (existing tests still pass, no observable difference). No speculative prep for slices beyond the next behavior slice.

Sequencing rules

  1. Stop-safe ordering — The user may decide to stop after any slice. The value delivered must be proportional to (or greater than) the number of completed slices, with close to zero waste if remaining slices are never implemented.
  2. Order by value — Earlier slices = higher user value and usability first.
  3. Many slices are good — Split as finely as you can while each slice still meets the type constraints above.
  4. Structure slices only justify themselves through the next behavior slice — A structure slice that is not immediately followed by the behavior slice it enables is speculative waste.

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 · 2,170 tokens per session scan A c751f0148430

Subscribe to this mod's changes

planning is a cursor rule published in the GitHub repository nerds-odd-e/doughnut (49 stars, last pushed 2d ago), licensed MIT. It adds 2,170 tokens to every session, about $0.0109 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.