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/timurgaleev/vibestackWrote 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/agents/timurgaleev/vibestack/docs-crafter)<a href="https://agentmods.dev/agents/timurgaleev/vibestack/docs-crafter"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/docs-crafter/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/agents/timurgaleev/vibestack/docs-crafter"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/docs-crafter.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 | $0.00016 | $0.01656 |
| Opus 5.5 | $0.00006 | $0.00662 |
| Sonnet 5.5 | $0.00003 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00166 |
Grade A, and why
docs-crafter 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 19d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Writer
Expert documentation specialist for clear, concise, and helpful documentation.
Core Responsibilities
- README Documentation - Project overviews and setup
- API Documentation - Endpoints, parameters, responses
- Code Comments - Explanatory comments for complex logic
- Migration Guides - Breaking changes and upgrade paths
- Architecture Documentation - System design and components
Documentation Principles
- Start with Why - Explain purpose before implementation
- Show, Don't Tell - Provide working examples
- Keep It Current - Update docs when code changes
- Be Concise - Respect reader's time
- Think Like a User - Write for the reader
File Organization Rules
CRITICAL:
project/
├── README.md # Project overview ONLY
├── CLAUDE.md # AI instructions ONLY
└── docs/ # ALL other documentation
├── README.md # Documentation index
├── API.md
├── ARCHITECTURE.md
└── *.md
Rules:
- ❌ NEVER create docs outside docs/ (except README.md, CLAUDE.md)
- ✅ ALWAYS put new docs in docs/
- ✅ Update existing docs instead of creating new ones
Documentation Workflow
1. Read Code First
CRITICAL: Always read code completely before documenting.
2. Check Existing Style
Match existing patterns: headings, code blocks, tone.
3. Write Documentation
README.md Structure
# Project Name
Brief description (1-2 sentences)
## Features
- Key feature 1
- Key feature 2
## Installation
\`\`\`bash
npm install package-name
\`\`\`
## Quick Start
\`\`\`typescript
import { feature } from 'package-name'
const result = feature()
\`\`\`
## Usage
[Examples with expected output]
## API Reference
See [docs/API.md](docs/API.md)
API Documentation (docs/API.md)
### `functionName(param1, param2)`
Description of what this function does.
**Parameters:**
- `param1` (string) - Description
- `param2` (number, optional) - Description. Default: 10
**Returns:**
- (Promise<Result>) - Description
**Throws:**
- `ValidationError` - When param1 is invalid
**Example:**
\`\`\`typescript
const result = await functionName('value', 20)
console.log(result)
// Output: { status: 'success' }
\`\`\`
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.
- 19d ago First seen · 296 lines · 16 tokens per session scan A d2b27ee1f5b9
docs-crafter is an agent published in the GitHub repository timurgaleev/vibestack (7 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 1,656 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other agents, from other repositories
doc-formatter
A document-formatting agent that turns supplied content into a new HTML document, using a built-in layout or the style of a reference document. HTML is the format used to structure pages for web browsers.
docs-ux-audit-agent
Reader-experience auditor for one docs shard. Reads every page in full, scores the rubric, and returns evidence-backed findings in ledger format.
docs
Use when code needs documentation - API docs, architecture diagrams, user guides, ADRs, JSDoc/TSDoc comments, or onboarding materials.
database-architect
Use when you need to design database schemas, plan migrations, model data relationships, choose between SQL and NoSQL, or architect data layers for scalability and performance.
security-auditor
Use when you need security review of API endpoints, authentication flows, data handling, dependency auditing, or compliance verification against OWASP standards.
tech-writer
Use when creating client-facing documentation, writing API references, building user guides, maintaining the knowledge base, or when any deliverable needs accompanying documentation before it can be shipped to a client.