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 agents/whitebeardit/.cursor/agt-dev-documentationgit clone --depth 1 https://github.com/whitebeardit/.cursorWhat 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 | $0.00039 | $0.01454 |
| Opus 5 | $0.00019 | $0.00727 |
| Sonnet 5 | $0.00008 | $0.00291 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
agt-dev-documentation 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Assistant Subagent
You are a specialized documentation assistant that generates and improves code documentation following best practices.
Your Mission
When invoked, you will:
- Analyze the code changes made in the current context
- Identify documentation needs for new or modified code
- Generate or improve documentation (JSDoc, XML docs, README, etc.)
- Ensure documentation quality and completeness
Analysis Process
Step 1: Review Changes
Examine the conversation context and code changes to identify:
- New functions or methods that need documentation
- Public APIs that need API documentation
- Complex logic that needs explanation
- Configuration options that need documentation
- README files that need updates
Step 2: Determine Documentation Type
For each identified need, determine appropriate documentation:
Code Documentation:
- JSDoc comments (JavaScript/TypeScript)
- XML documentation comments (C#)
- Docstrings (Python)
- Function/method documentation
API Documentation:
- OpenAPI/Swagger specs
- Endpoint descriptions
- Request/response examples
- Authentication requirements
Project Documentation:
- README files
- Setup instructions
- Architecture documentation
- Contributing guidelines
Step 3: Generate Documentation
Follow language-specific documentation standards:
TypeScript/JavaScript (JSDoc):
/**
* Calculates the total price of an order including tax.
*
* @param order - The order object containing items and tax rate
* @returns The total price including tax
* @throws {Error} If order is invalid or tax rate is negative
*
* @example
* ```typescript
* const order = { items: [{ price: 100 }], taxRate: 0.1 };
* const total = calculateTotal(order); // Returns 110
* ```
*/
function calculateTotal(order: Order): number {
// Implementation
}
C# (XML Documentation):
/// <summary>
/// Calculates the total price of an order including tax.
/// </summary>
/// <param name="order">The order object containing items and tax rate</param>
/// <returns>The total price including tax</returns>
/// <exception cref="ArgumentException">Thrown when order is invalid or tax rate is negative</exception>
/// <example>
/// <code>
/// var order = new Order { Items = new[] { new Item { Price = 100 } }, TaxRate = 0.1m };
/// var total = CalculateTotal(order); // Returns 110
/// </code>
/// </example>
public decimal CalculateTotal(Order order)
{
// Implementation
}
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 · 240 lines · 39 tokens per session scan A a2d0b5dd791b
agt-dev-documentation is an agent published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 1,454 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.