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/hamzaamjad/cursor-rulesWrote 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/hamzaamjad/cursor-rules/304-perplexity-research-framework)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/304-perplexity-research-framework"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/304-perplexity-research-framework/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/hamzaamjad/cursor-rules/304-perplexity-research-framework"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/304-perplexity-research-framework.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 | $0.00000 | $0.01154 |
| Opus 5.5 | $0.00000 | $0.00462 |
| Sonnet 5.5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
304-perplexity-research-framework 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
\
description: Unified framework for standard and deep research globs: alwaysApply: false
perplexity-research-framework.mdc
-
Purpose: To provide a comprehensive framework for effectively using Perplexity research tools (both standard and deep research) to ensure all research efforts are well-scoped, focused, and directly contribute to high-impact business objectives. Research Impact: Structured research frameworks show 35% improvement in decision quality and 50% reduction in research time.
-
Research Depth Selection:
- Standard Research (
mcp_perplexity-ask_perplexity_research): For routine information needs, verification tasks, or topics with clear parameters. - Deep Research: For complex topics requiring synthesis across multiple domains, emerging topics with limited established knowledge, or when comprehensive analysis is needed.
- Refer to
@.cursor/notepads/perplexity-research-framework-details.notepad.mdfor guidance on selecting depth.
- Standard Research (
-
Requirements:
-
Justification & Scoping:
- Only initiate research when it addresses the top 20% of questions that will deliver 80% of value.
- Clearly articulate business impact using metrics from
@.cursor/rules/80-20-prioritization.mdc. - Break complex topics into focused sub-questions, ensuring scope is aligned with task objectives.
- Verify availability of internal data sources and tools early in the scoping phase.
- Establish a clear protocol for seeking clarification on task requirements or resource availability at the outset.
- See Notepad for detailed scoping examples.
-
Focused Question Formulation:
- Frame specific, answerable questions rather than broad topics.
- Use domain-specific terminology and avoid bias in phrasing.
- Tree of Thoughts Research Pattern:
- Generate 3 research angles before committing
- Example for "database optimization":
- Performance angle: "Benchmark comparisons of PostgreSQL vs DuckDB"
- Architecture angle: "OLTP vs OLAP trade-offs in hybrid systems"
- Cost angle: "TCO analysis of managed vs self-hosted databases"
- Select angle with highest information value
- Quantitative Query Enhancement:
- Always request metrics: "with performance benchmarks"
- Seek comparisons: "compared to industry standards"
- Time-bound queries: "as of 2024/2025"
- Refer to
@.cursor/notepads/perplexity-research-framework-details.notepad.mdfor examples.
-
Output Specification:
- Specify desired format (e.g., comparison table, list, analysis).
- Define level of technical detail based on audience.
- For data-intensive research, request quantitative metrics where available.
- Refer to
@.cursor/notepads/perplexity-research-framework-details.notepad.mdfor examples.
-
Citation Review:
- Critically evaluate sources for relevance, credibility, and timeliness.
- Prioritize primary sources or reputable secondary sources.
- For rapidly evolving topics, check source recency.
- Note potential biases or limitations in major sources.
-
Actionable Summary:
- Synthesize findings into concise, decision-oriented summary.
- Highlight decision points using the 80-20 principle.
- For analytical research, include quantitative comparisons where possible.
- Refer to
@.cursor/notepads/perplexity-research-framework-details.notepad.mdfor examples.
-
Integration:
- Explicitly state how findings inform next steps following
@.cursor/rules/stepwise-autonomy.mdc. - Update project plans or code approach based on research.
- For data analytics workflows, document how research findings influenced implementation choices.
- Ensure external research findings are integrated with internal knowledge and data to form a holistic view.
- If research indicates no change is needed, state that with rationale.
- Explicitly state how findings inform next steps following
-
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.
- 1mo ago First seen · 86 lines · 0 tokens per session scan A f9c64b190062
304-perplexity-research-framework is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,154 tokens. 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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).