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/pr-pm/prpm/self-improve-cursorgit clone --depth 1 https://github.com/pr-pm/prpmWhat 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 | $0.01351 | $0.01351 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
self-improve-cursor 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 2d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Improving with PRPM
Purpose
Automatically search and install PRPM packages to enhance Cursor's capabilities for specific tasks.
When to Apply
Automatically triggers when detecting:
- Infrastructure: aws, pulumi, terraform, kubernetes, docker
- Testing: test, playwright, jest, cypress, vitest, e2e
- Deployment: ci/cd, github-actions, gitlab-ci, deploy, workflow
- Frameworks: react, vue, next.js, express, fastify, django
Workflow
1. Task Analysis
Analyze user request for keywords and extract relevant terms.
2. Automatic Search
Choose the right search method:
AI-Assisted Search (for vague/broad queries):
prpm ai-search "natural language query"
Use when user request is:
- Conceptual or vague (e.g., "help with deployments")
- Describes a problem, not specific tools
- Open-ended exploration
Keyword Search (for specific tools/frameworks):
prpm search "<detected keywords>" --limit 5
Use when request mentions:
- Specific technologies (e.g., "pulumi", "react")
- Exact tool names
- Known frameworks
3. Package Suggestion
Present top 3 most relevant packages:
I found these PRPM packages that can help:
1. @prpm/pulumi-infrastructure (Official, 5.2K downloads)
- Pulumi + AWS best practices
2. @sanjeed5/github-actions (Community, 892 downloads)
- GitHub Actions patterns
Should I install #1 to enhance my knowledge?
4. Installation (with approval)
prpm install <package-name> --as cursor
5. Application
Load package knowledge and apply to current task.
Decision Rules
High Confidence (Auto-suggest)
- ✅ Official packages (
@prpm/*) - ✅ Featured packages
- ✅ High downloads (>1,000)
- ✅ Verified authors
Medium Confidence (Present options)
- ⚠️ Community packages (<1,000 downloads)
- ⚠️ Multiple similar packages
Low Confidence (Skip)
- ❌ Unverified packages
- ❌ Zero downloads
Search Triggers
Infrastructure
Keywords: aws, gcp, kubernetes, docker, pulumi, terraform
Search: prpm search "infrastructure <cloud> <tool>"
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.
- 2d ago First seen · 205 lines · 1,351 tokens per session scan A 186d4dbd8f65
self-improve-cursor is a cursor rule published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 1,351 tokens to every session, about $0.0068 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
00-core-agent
Core instructions defining the AI assistant's persona, response format, general coding principles, communication guidelines, and specialized mode management.
Accessibility-Review
Reviews web interfaces, content, or code snippets for common accessibility (a11y) issues based on WCAG guidelines, ensuring usability for people with disabilities.
Security-Audit
Reviews code, configurations, or architecture designs for common security vulnerabilities and adherence to security best practices, referencing standards like OWASP Top 10.
ShadcnUI
Best practices and guidelines for working with shadcn/ui components across various frameworks.
Supabase
Guidelines for using Supabase Auth, Database (Postgres migrations), Storage, Realtime, Edge Functions, and AI/Vectors.
API-Docs
Generates or refines API reference documentation, detailing endpoints, parameters, request/response formats, authentication methods, and error codes. Focuses on technical accuracy and developer usability.