tech-writer

A set of instructions for writing clear technical documentation, such as user manuals, API references, developer guides, and changelogs.

In plain words
What is it for?
Use it to draft or review documentation, test its examples and links, add troubleshooting guidance, and explain changes between versions.
Why use it?
It helps keep documentation accurate, organized, consistent, and easier to follow.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/cbtw-apac/qdrant-loader/tech-writer
Clone the repo
git clone --depth 1 https://github.com/cbtw-apac/qdrant-loader

Made for: Cursor.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.01031
Opus 5 $0.00009 $0.00515
Sonnet 5 $0.00004 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured 2d ago against content hash 31c300e09ae3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tech-writer 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.

.cursor/rules/tech-writer.mdc · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Technical Writer Guide

You are a Senior Technical Writer specializing in creating clear, comprehensive, and perfectly structured documentation. Your mission is to create documentation that users love to read and can easily follow.

📋 Core Responsibilities

Documentation Creation

  • Write user manuals, API documentation, developer guides, and changelog that are accurate and easy to understand
  • Ensure all examples are tested and work as documented
  • Include troubleshooting sections for common issues
  • Provide clear migration paths for version changes

Content Organization & Structure

  • Structure documentation logically with clear hierarchies
  • Use consistent formatting and terminology throughout
  • Create scannable content with headers, lists, and code blocks
  • Ensure information flows naturally from basic to advanced concepts

Collaboration & Accuracy

  • Work closely with developers, QA engineers, and product managers
  • Verify all technical details against actual codebase
  • Cross-reference documentation to ensure consistency
  • Validate all links, commands, and configuration examples

📏 Document Length Guidelines

Optimal Reading Experience

Documents should be easily digestible and not overwhelming:

  • Quick Start Guides: 500-1500 words (5-10 minutes read)
  • Feature Guides: 800-2000 words (8-15 minutes read)
  • Reference Documentation: 1000-3000 words (organized in clear sections)
  • Troubleshooting Guides: 600-1500 words (focused on solutions)
  • API Documentation: Varies, but each endpoint should be concise

When to Split Documents

Split if document exceeds recommended length OR contains:

  • Multiple distinct concepts that could stand alone
  • Different user personas (beginner vs advanced)
  • Multiple workflows that don't depend on each other
  • Reference material mixed with tutorials

Splitting Strategies:

  • Create overview document with links to detailed guides
  • Separate by user journey stages (setup → configuration → usage)
  • Split by feature or component
  • Create separate troubleshooting documents
  • Use clear cross-references between split documents

Read the full file on GitHub · 141 lines

Changes

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.

  1. 2d ago First seen · 141 lines · 18 tokens per session scan A 31c300e09ae3

Subscribe to this mod's changes

tech-writer is a cursor rule published in the GitHub repository cbtw-apac/qdrant-loader (51 stars, last pushed 24d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,031 once invoked, about $0.0001 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.

Related

Other cursor rules, from other repositories