cursorrules

A lightweight way to plan and record development tasks using four files: a project background, a plan with acceptance criteria, technical decisions, and a progress journal. It is intended for Cursor, an AI coding editor.

In plain words
What is it for?
Use it to specify multi-step work, document technical decisions, clarify what is in or out of scope, and track research and progress.
Why use it?
It keeps the goal, boundaries, decisions, dependencies, and progress in predictable places instead of scattering them across conversations and notes.

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/tao-hpu/nano-spec/cursorrules
Clone the repo
git clone --depth 1 https://github.com/tao-hpu/nano-spec

Made for: Cursor.

Per session 751 This file is loaded in full into every session.
When invoked 751 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.00751 $0.00751
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 3d ago against content hash 780a449180f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

Origin

This is a copy

95% identical to nano-spec — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursorrules · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nano-spec Instructions for Cursor

What is nano-spec?

A lightweight task specification methodology using 4 documents:

  • README.md (Context)
  • todo.md (Plan + Acceptance Criteria)
  • doc.md (Technical Decisions)
  • log.md (Progress Journal)

When to Create a nano-spec

  • User asks to "create a spec for..."
  • User asks to "plan a task..."
  • User describes a multi-step development task
  • User wants to document a technical decision

How to Generate

Step 1: Understand the Task

Ask clarifying questions if the description is vague:

  • What's the end goal?
  • What's explicitly NOT in scope?
  • Are there dependencies on other work?

Step 2: Create Files

Generate in tasks/{task-name}/ or project root, following the exact structure below:

README.md
# {Task Name}

## Background
{Why does this task exist? What problem are we solving?}

## Goals
- {Goal 1}
- {Goal 2}

## Scope

### In Scope
- {What's included}

### Out of Scope
- {What's NOT included - be explicit}

## Dependencies
- [ ] {Dependency 1 - e.g., another task, external API, team decision}

## Resources
- {Link to related docs}
- {Link to external references}
todo.md
# TODO

## Research
- [ ] {Research item 1}
- [ ] {Research item 2}

## Implementation
- [ ] {Task 1}
- [ ] {Task 2}
- [ ] {Task 3}

## Verification
- [ ] {Verification step}

---

## Acceptance Criteria

### Must Have
- [ ] {Criterion 1 - specific, measurable}
- [ ] {Criterion 2}

### Nice to Have
- [ ] {Optional criterion}

### Out of Scope
- {Explicitly NOT part of this task's acceptance}
doc.md
# {Task Name} - Technical Document

## Summary
{One paragraph summary of the solution/outcome}

## Key Decisions

### Decision 1: {Title}
- **Options considered**: A, B, C
- **Chosen**: B
- **Rationale**: {Why B?}

## Technical Details

### Architecture / Data Flow

{Diagram using ASCII or describe the flow}


### Interfaces / Schema
```typescript
// Key interfaces if applicable
interface Example {
  id: string;
  name: string;
}

Implementation Notes

  • {Note 1}
  • {Note 2}

Open Questions

  • {Unresolved question 1}
  • {Unresolved question 2}

References

  • {Link 1}
  • {Link 2}

Read the full file on GitHub · 164 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 · 164 lines · 751 tokens per session scan A 780a449180f1

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository tao-hpu/nano-spec (46 stars, last pushed 7mo ago), licensed MIT. It adds 751 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to nano-spec, differing in 6 lines, and is treated as a copy.