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/mhmdreza-rafiei/agent-toolsWrote 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/mhmdreza-rafiei/agent-tools/prompt-quality)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/prompt-quality"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/prompt-quality/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/mhmdreza-rafiei/agent-tools/prompt-quality"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/prompt-quality.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 | $0.00033 | $0.00375 |
| Opus 5 | $0.00016 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
prompt-quality 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 8d 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.
What it actually says
Prompt quality
Applies when writing or enhancing prompts, or authoring new agent instructions. Load for enhance-prompt or for new agent development. Not every chat - only when prompt quality is a concern.
Clarity and precision
- Specific verbs: Prefer create to make, implement to do.
- Concrete nouns: API endpoint instead of stuff.
- Unambiguous scope: State what is in scope, and what is explicitly out.
- Audience: Write for the target agent (if known), or a general implementer.
Output format
- Specify format: Always state the desired output format (Markdown, JSON, code block).
- Structure: If structured output is expected, give a template or example.
- Completeness: Define what a complete answer looks like.
Measurability
- Acceptance criteria: For tasks, include 1-3 measurable acceptance criteria. These allow the implementing agent to self-verify.
- Verification steps: Explicitly state how the output can be verified.
Must-nots
- Forbidden actions: Explicitly state actions that must NOT be taken. These act as guardrails (e.g. no breaking changes, do not modify X).
- Exclusions: State things that are out of scope or should not be included.
Do not
- Invent requirements: Never assume or invent requirements the user did not state.
- Inject local context: Avoid workspace-local paths, stack, credentials.
- Be vague: Avoid words like improve, make better without concrete definitions.
- Conflate what with how: Separate the desired outcome from implementation details.
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.
- 8d ago First seen · 44 lines · 33 tokens per session scan A fb340b1e5ce9
prompt-quality is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 33 tokens to every session and 375 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 2026-09-03.
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-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.