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/tao-hpu/nano-spec/cursorrulesgit clone --depth 1 https://github.com/tao-hpu/nano-specWhat 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 | $0.00751 | $0.00751 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
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.
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.
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}
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 · 164 lines · 751 tokens per session scan A 780a449180f1
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.
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.