ai-dev-os-plan

ai-dev-os-plan is a cursor rule for coding agents from yunbow/ai-dev-os-plugin-cursor. It costs 47 tokens per session (605 once invoked), scanned A, original, MIT.

A planning rule for software changes that reviews the project’s instructions and creates a checklist before coding begins.

In plain words
What is it for?
Use it to plan a feature, bug fix, refactoring, or other code change and request approval before implementation.
Why use it?
It reduces the risk of changing the wrong files or missing rules documented in files such as .cursorrules, CLAUDE.md, or AGENTS.md.

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/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-plan
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-cursor

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-dev-os-plan

README.md
[![agentmods](https://agentmods.dev/badge/rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-plan.svg)](https://agentmods.dev/rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-plan)
Your own site
<a href="https://agentmods.dev/rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-plan"><img src="https://agentmods.dev/badge/rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00047 $0.00605
Opus 5 $0.00023 $0.00302
Sonnet 5 $0.00009 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured 3d ago against content hash 24fc646dd50e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-dev-os-plan 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 3d 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/ai-dev-os-plan.mdc · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Dev OS Implementation Plan

Execution Flow

1. Analyze the Request

Parse the user's implementation request and identify:

  • Goal: What needs to be built or changed
  • Scope: New feature / bug fix / refactoring / enhancement
  • Affected area: Which parts of the codebase are involved

2. Identify Affected Files

Search the codebase to determine:

  • Files that will be modified
  • Files that will be created
  • Files that will be deleted
  • Related files that provide context (imports, tests, configs)

3. Parse .cursorrules and Load Guidelines

Extract the list of guideline file paths from the project's .cursorrules (or CLAUDE.md / AGENTS.md). Read the referenced guideline files to understand the active rules.

4. Build Dynamic Mapping

Map affected files to their relevant guidelines using file pattern matching.

If checklist templates exist in .cursor/checklist-templates/ for the detected tech stack, load them as a reference.

5. Extract Relevant Checklist Items

From the mapped guidelines, extract items relevant to this specific change:

  • Filter by keywords: "MUST", "MUST NOT", "PROHIBITED", "REQUIRED"
  • If a guideline has checklist: [...] in frontmatter, use those items
  • Discard items unrelated to the current scope

6. Present the Plan

## Implementation Plan

### Goal
> [One-line summary]

### Scope
- Type: [new feature / bug fix / refactoring / enhancement]
- Risk: [low / medium / high]

### Changes
| Action | File | Description |
|--------|------|-------------|

### Implementation Steps
1. ...

### Guideline Checklist
> Auto-generated from AI Dev OS guidelines applicable to this change.

#### [guideline-file-1.md]
- [ ] Rule 1
- [ ] Rule 2

### Principles to Keep in Mind
> From L2 principles relevant to this change.
- [Principle 1]: [Brief explanation]

7. Wait for Approval

  • Approve: Proceed
  • Modify: Update and re-present
  • Cancel: Abort

8. Implement

Upon approval:

  1. Implement each step
  2. Check off guideline items after each file change
  3. Output checklist completion summary

Read the full file on GitHub · 87 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. 3d ago First seen · 87 lines · 47 tokens per session scan A 24fc646dd50e

Subscribe to this mod's changes

ai-dev-os-plan is a cursor rule published in the GitHub repository yunbow/ai-dev-os-plugin-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 605 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.