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/holasoymalva/readme-generator-toolkit/improve-readmegit clone --depth 1 https://github.com/holasoymalva/README-Generator-ToolkitWrote 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/holasoymalva/readme-generator-toolkit/improve-readme)<a href="https://agentmods.dev/rules/holasoymalva/readme-generator-toolkit/improve-readme"><img src="https://agentmods.dev/badge/rules/holasoymalva/readme-generator-toolkit/improve-readme.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.01340 |
| Opus 5 | $0.00004 | $0.00670 |
| Sonnet 5 | $0.00002 | $0.00268 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
improve-readme 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: Improve Existing README
Goal
To guide an AI assistant in analyzing and improving an existing README.md file, making it more comprehensive, clear, and professional while maintaining the original intent and structure.
Process
-
Receive Existing README: The user provides their current README.md file using @ tag (e.g., @README.md).
-
Analyze Current README: Systematically evaluate the existing documentation for:
- Content completeness and accuracy
- Structure and organization
- Clarity and readability
- Visual appeal and formatting
- Missing essential sections
- Outdated or incorrect information
-
Identify Improvement Areas: Categorize findings into:
- Missing Sections: Essential parts not included
- Unclear Content: Confusing or poorly explained sections
- Formatting Issues: Poor structure, inconsistent styling
- Outdated Information: Old versions, broken links, deprecated instructions
- Enhancement Opportunities: Ways to make it more engaging or useful
-
Ask Targeted Questions: Based on analysis, ask specific questions:
- Focus Areas: "Which sections are most important to improve: [list identified issues]?"
- Audience: "Has your target audience changed since the original README?"
- Recent Changes: "Have there been updates to the project not reflected in the README?"
- Specific Goals: "Are there particular aspects you want to emphasize more?"
- Style Preferences: "Do you prefer a more technical or user-friendly tone?"
-
Generate Improved README: Create an enhanced version addressing identified issues.
-
Save File: Update the existing README.md or create README-improved.md for comparison.
Analysis Framework
Content Analysis
- Completeness: Does it cover all essential aspects of the project?
- Accuracy: Are instructions current and correct?
- Clarity: Can a new user follow the documentation successfully?
- Examples: Are there practical, working examples?
- Context: Does it explain the "why" not just the "how"?
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.
- 4d ago First seen · 159 lines · 8 tokens per session scan A d75eeaa85191
improve-readme is a cursor rule published in the GitHub repository holasoymalva/README-Generator-Toolkit (4 stars, last pushed 1y ago), licensed Apache-2.0. It adds 8 tokens to every session and 1,340 once invoked, about $0.0000 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
propose-test-cases
Propose comprehensive test cases for PR changes.
detect-code-smells
Detect code smells and anti-patterns in PR changes.
suggest-improvements
Provide actionable improvement suggestions for PR changes.
analyze-pr-changes
Comprehensive analysis of Pull Request changes.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.