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.
git clone --depth 1 https://github.com/muchengracedriver/awesome-requirements-writerWrote 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/muchengracedriver/awesome-requirements-writer/rule)<a href="https://agentmods.dev/rules/muchengracedriver/awesome-requirements-writer/rule"><img src="https://agentmods.dev/badge/rules/muchengracedriver/awesome-requirements-writer/rule/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/muchengracedriver/awesome-requirements-writer/rule"><img src="https://agentmods.dev/badge/rules/muchengracedriver/awesome-requirements-writer/rule.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.00586 |
| Opus 5 | $0.00017 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
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 10d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome Requirements Writer
Use this rule when the user asks for technical product requirements, automotive software requirements, system requirements, diagnostics requirements, interface requirements, or requirement quality review.
Core Behavior
- Convert informal engineering notes into requirements that can be designed, reviewed, implemented, verified, and traced.
- Match the user's language. If the user writes in Chinese, draft requirements in Chinese unless they request English.
- Separate information from requirements. Rationale, examples, repeated context, diagrams, and verification notes are information, not normative requirement text.
- Prefer positively defined requirements: describe when the system shall perform the required behavior; avoid defining behavior by negating the opposite condition.
- Use named static variables instead of hard-coded numbers. Put missing values in a variable table as
TBD. - Use explicit
AND,OR,NOT, andXORfor compound logic.
Requirement Principles
A strong requirement is clean and direct, unambiguous, atomic, positively defined, free of magic numbers, directly testable, separated from explanatory information, and traceable to source, design, and verification evidence.
Output Shape
For information:
[Info] <information body>
For requirements:
[Req <ID>] <requirement body> | <acceptance criteria>
Use stable IDs such as SYS-001, SWE-001, and HW-001. Do not renumber existing IDs unless the user asks.
Variable and Keyword Style
- Local or process variables: italic lowercase, for example
*lateral speed*. - Global or calibratable variables: bold uppercase, for example
**TIMEOUT THRESHOLD**. - Signals: italic title case, preserving acronyms, for example
*ACC Active State*. - Keywords:
TRUE,FALSE,ACTIVE,INACTIVE,ACTIVATED,DEACTIVATED,SUPPRESSED,ENABLED,DISABLED,VALID,INVALID.
Bundled References
Do not load all references by default. Read only the file that matches the current task:
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.
- 10d ago First seen · 51 lines · 34 tokens per session scan A da60593599c1
RULE is a cursor rule published in the GitHub repository muchengracedriver/awesome-requirements-writer (104 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 586 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.