plan_sections_rules

A planning rule that requires relevant plans to cover goals, problems, solutions, and automated tests. Automated tests are checks run by software to verify that code still works.

In plain words
What is it for?
It helps structure plans for features, integrations, workflows, architecture changes, and regressions while omitting sections that do not apply.
Why use it?
It keeps plans focused on the desired outcome, the current issue, the proposed response, and how the work will be checked.

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/markmhendrickson/foundation/plan_sections_rules
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/foundation

Made for: Cursor.

Per session 355 This file is loaded in full into every session.
When invoked 355 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 $0.00355 $0.00355
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash c40b95943eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan_sections_rules 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.

.cursor/rules/plan_sections_rules.mdc · 36 lines

What it actually says

Plan Sections

When creating or updating a plan, structure it around the decision the user needs to make and the work that will follow.

Requirements

  • Include a Goals section when the plan would benefit from a clear statement of desired outcomes.
  • Include a Problems section when the plan is addressing pain points, failure modes, blockers, or current-state gaps.
  • Include a Solutions section when the plan proposes concrete approaches, design responses, or implementation choices.
  • Include an Automated tests section when testing is relevant to the work, especially for code changes, integrations, workflows, or regressions.
  • Omit any of these sections only when they would be empty, redundant, or not useful for the specific plan.

Guidance

  • Keep the sections concise and proportional to the scope of the plan.
  • Use explicit section headings so the structure is easy to scan.
  • For small plans, each section can be brief; the requirement is about coverage, not verbosity.
  • Do not force the Automated tests section for plans where no meaningful automated verification exists, but address testing whenever it materially reduces risk.

Examples

Good

  • A feature or architecture plan with Goals, Problems, Solutions, and Automated tests.
  • A lightweight operational plan with Goals and Solutions, while omitting Automated tests if no testable system change is involved.

Bad

  • A plan that jumps straight into tasks without clarifying the problem being solved.
  • A code-change plan that omits testing considerations even though regressions are plausible.
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 · 36 lines · 355 tokens per session scan A c40b95943eff

Subscribe to this mod's changes

plan_sections_rules is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 355 tokens to every session, about $0.0018 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.