cursor-rule

A project rule that tells coding agents not to leave temporary notes, plans, or reports in the project’s top folder. It also defines preferred folders for temporary files, reports, and formal documentation.

In plain words
What is it for?
It is for keeping agent-created files organized, protecting files such as README.md and LICENSE, and checking where temporary or requested documents should go.
Why use it?
It reduces clutter and prevents agents from modifying protected documentation files without permission.

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/phoenix0531-sudo/tidy-skill/cursor-rule
Clone the repo
git clone --depth 1 https://github.com/Phoenix0531-sudo/tidy-skill
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 353 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 $0.00000 $0.00353
Opus 5 $0.00000 $0.00177
Sonnet 5 $0.00000 $0.00071
Haiku 4.5 $0.00000 $0.00035

Measured 2d ago against content hash 06f63cb7f076, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-rule 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.

skills/tidy-skill/templates/cursor-rule.mdc · 34 lines

What it actually says

洁癖.skill Rule for Cursor

Do Not

  • Create plan.md, todo.md, summary.md, notes.md, lessons.md, report.md, final_report.md, work_summary.md, changes_summary.md, implementation_plan.md, migration_plan.md, audit_report.md, cleanup_report.md, task_list.md, or progress.md in the project root.
  • Generate end-of-task summary files unless the user explicitly requests it.
  • Write a plan to disk when the user asked for a plan in chat.

Do

  • Keep plans, todos, summaries, and progress in the chat reply.
  • Use .agent_tmp/ for any temporary file. Prefix with a date/task context.
  • Use .agent_reports/ for user-requested deliverable documents.
  • Put formal documentation under docs/ — and only when asked.
  • Run the Artifact Intent Check before creating any file:
1. User requested a file?           yes / no
2. Purpose:
3. Reader:
4. Expected lifetime:               session / days / persistent / formal-doc
5. Destination path:
6. Why a chat response is not enough:

Protected Files

Never modify without explicit request: README.md, CHANGELOG.md, LICENSE, CONTRIBUTING.md, everything under docs/.

End of Task

Before finishing: clean your temp files from .agent_tmp/, verify no files were left in the root unintendedly.

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 · 34 lines · 0 tokens per session scan A 06f63cb7f076

Subscribe to this mod's changes

cursor-rule is a cursor rule published in the GitHub repository Phoenix0531-sudo/tidy-skill (20 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 353 tokens. 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.