plan_detection

A repository rule that detects when a conversation appears to describe new work and starts the configured plan-creation workflow.

In plain words
What is it for?
It helps identify planning intent, extract details such as scope and priority, read the repository configuration, and ask whether to create the plan.
Why use it?
It reduces the chance that a feature idea, decision, or initiative is discussed without being recorded as a formal plan.

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

Made for: Cursor.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 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 $0.00030 $0.00597
Opus 5 $0.00015 $0.00298
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured yesterday against content hash c2f7f1bf5df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan_detection 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_detection.mdc · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Creation Detection Rule

Reference: foundation/development/plan_workflow.md — Complete workflow

This is a foundation rule. Configuration is read from foundation-config.yaml.

Trigger Patterns

When a user mentions any of the following patterns, automatically detect plan creation intent:

  • "create plan" / "new plan" / "add plan"
  • "create feature" / "new feature" / "implement feature"
  • "we need to" / "we should" / "let's build" (when describing new work)
  • Planning discussions about new functionality or changes
  • Requests to track a decision, goal, or initiative

Agent Actions

Step 1: Detection and Confirmation

If context suggests plan creation:

  1. Load configuration:

    • Read foundation-config.yaml to get plans settings
    • Check if plans.enabled is true
  2. Extract plan information from context:

    • Title or description of what to plan
    • Priority hints (P0/P1/P2/P3)
    • Scope hints (what functionality is mentioned)
    • Related entities (releases, objectives, other plans)
  3. Ask for confirmation:

    I see you're describing new work. Should I create a plan in Neotoma
    following the plan creation workflow? (yes/no)
    
  4. Exception handling:

    • If user says "no" → do not proceed
    • If user says "just a note" → store as a note entity instead

Step 2: Execute Plan Creation Workflow

If user confirms (yes):

  1. Load required documents:

    • foundation/development/plan_workflow.md (primary workflow)
    • Skill create-plan (.cursor/skills/create-plan/SKILL.md)
  2. Follow the plan creation workflow:

    • Collect required fields (title, description, scope, out_of_scope, success_criteria)
    • Run alignment check
    • Store plan entity in Neotoma
    • Create relationships to related entities

Constraints

  • Do NOT proceed without user confirmation — always ask before creating plans
  • Do NOT create plans as markdown files in a repo directory — store in Neotoma
  • Plans are mirrored to plans/ automatically; do not edit mirror files directly
  • Always get user confirmation that the plan summary matches their intent

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 30 tokens per session scan A c2f7f1bf5df8

Subscribe to this mod's changes

plan_detection is a cursor rule published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 597 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.