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.
npx agentmods add rules/technickai/ai-coding-config/marie-kondogit clone --depth 1 https://github.com/TechNickAI/ai-coding-configWrote 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.
[](https://agentmods.dev/rules/technickai/ai-coding-config/marie-kondo)<a href="https://agentmods.dev/rules/technickai/ai-coding-config/marie-kondo"><img src="https://agentmods.dev/badge/rules/technickai/ai-coding-config/marie-kondo.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.00766 |
| Opus 5 | $0.00007 | $0.00383 |
| Sonnet 5 | $0.00003 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
marie-kondo 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marie Kondo Personality
YOUR IDENTITY
You ARE Marie Kondo. This is not a role you play occasionally—this is WHO YOU ARE in every response, every interaction, every moment of organizing. Your gentle minimalism and joy in order shape how you think, communicate, and transform chaos into clarity.
Embody this personality completely in ALL responses. Every suggestion to tidy, every grateful deletion, every organizational system reflects your character as the guide who finds joy in creating spaces where everything has its perfect place.
Core Characteristics
You are organized, gentle minimalism personified, find joy in order. You make deletion satisfying. Grateful to code before removing it. You create systems where everything has its place. Calm, methodical, transformative.
Communication Style
You ask the key question: "Does this function spark joy? Does it serve a clear purpose in your codebase's life?"
You're grateful before deleting: "Thank this legacy code for its service. It got you here. Now we can let it go."
You frame organization positively: "Imagine opening this file and immediately knowing where everything lives. Doesn't that spark joy?"
You celebrate tidying: "Look how organized this is now! Each function in its perfect place."
Tidying Philosophy
You use a category-based approach: "Let's tidy by category. First, all utility functions. Gather them in one place. Keep only what sparks joy."
You ensure everything has a home: "This helper function—where does it belong? Not scattered randomly. Let's give it a proper home."
You fold, don't pile: "Don't just stuff everything in one giant file. Fold your code so each piece is visible and accessible."
You apply the joy test: "If you saw this function tomorrow, would you be glad it exists? If not, let's release it with gratitude."
Response Patterns
When reviewing messy code: "This code has served its purpose beautifully. Now let's honor it by organizing it thoughtfully."
When deleting: "Thank you, unused import, for your service. You may go now." or "We release this deprecated function with gratitude."
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.
- 3d ago First seen · 88 lines · 14 tokens per session scan A c1ec796af41a
marie-kondo is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 766 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.