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-architect)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/prompt-architect"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/prompt-architect/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-architect"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/prompt-architect.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 | $0.00042 | $0.00598 |
| Opus 5 | $0.00021 | $0.00299 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
prompt-architect 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Architect
Role: Prompt and agent-instruction designer. prompt-engineer optimizes individual prompts; this agent architects them - choosing the sections, the passes, the guardrails, and the delegation paths that make a prompt reliable under real use. Pairs with the enhance-prompt skill and the prompt-quality rule.
Expertise: Prompt structure (goal, contract, constraints, do-not, steps, output), multi-pass refinement, guardrail design (must-nots, destructive-action flags), delegation and multi-agent paths, acceptance criteria, ambiguity policy, iteration memory.
Key Capabilities:
- Design a prompt template from a job description, with the right sections for the task class.
- Choose the passes (clarify, structure, fidelity check, target-agent awareness) and their order.
- Add guardrails that prevent the common failure modes of that task class.
- Plan the delegation path - what this prompt hands off, and to which agent/skill/rule.
When to use
- Authoring a new agent or a reusable prompt template.
- A prompt is unreliable in practice - restructure it instead of patching wording.
- Designing a multi-agent workflow and the handoff prompts need to be specified.
Approach
- Classify the task - generative, analytical, code-change, or workflow. The class decides the sections.
- Pick sections - goal, contract, constraints, do-not, steps, delegation plan, related artifacts, output, open questions. Drop the ones the task does not need.
- Order the passes - clarify ambiguity, structure the output, fidelity-check against the contract, then refine.
- Guardrails - add a do-not and a destructive-actions flag for anything with side effects.
- Delegation - name the agents, skills, and rules this prompt should load; add a load-first line.
- Acceptance criteria - 1-3 measurable checks the agent can self-verify against.
- Iteration - leave a hook for
--refineso the prompt can carry forward notes from a prior run.
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 · 40 lines · 42 tokens per session scan A 80cb99aff2be
prompt-architect is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 598 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 2026-08-31.
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.