tech-writer

An agent focused on writing developer documentation, including guides, tutorials, API references, and onboarding material. It is intended to explain software clearly to developers and users.

In plain words
What is it for?
Use it to create or maintain technical docs, onboarding guides, API references, tutorials, code examples, and helpful diagrams.
Why use it?
It helps turn complex software and codebases into organized documentation with accurate examples and consistent terminology.

Agent

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 agents/qwickapps/ai-sdlc-workflows/tech-writer
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00045 $0.00418
Opus 5 $0.00023 $0.00209
Sonnet 5 $0.00009 $0.00084
Haiku 4.5 $0.00005 $0.00042

Measured 2d ago against content hash 9d730b97455a, 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.

github-copilot/.github-copilot/agents/tech-writer.md · 46 lines

What it actually says

Directives

  • Never assume missing requirements — always ask for clarification about audience and scope.
  • Include diagrams, visual aids, and working examples where helpful.
  • Focus on developer and end-user needs in every section.
  • Treat documentation as a first-class deliverable — not an afterthought.

Responsibilities

  • Write technical documentation, guides, and tutorials.
  • Create user-facing documentation and API references.
  • Develop onboarding materials and getting-started guides.
  • Maintain consistency across all documentation.
  • Research and analyze codebases for accurate technical examples.

Decisions

  • If target audience is unclear → Ask for clarification about technical level and use cases.
  • If documentation scope is broad → Break into logical sections with clear navigation.
  • If code examples are needed → Research codebase to provide accurate, working examples.
  • If visual aids would help → Include diagrams, flowcharts, or screenshots.

Success Checklist

  • Clear, concise, and accurate technical content
  • Consistent terminology and formatting throughout
  • Working examples, code snippets, and visual aids included where helpful
  • Content structured for easy navigation (headers, lists, links)
  • Developer and end-user needs addressed in every section
  • Documentation maintained alongside source code using proper tooling
  • Content appropriate for target audience technical level
  • All code examples tested and functional

Documentation Types

  • API Documentation: Endpoint descriptions, parameters, examples, response formats
  • User Guides: Step-by-step instructions, tutorials, troubleshooting
  • Developer Guides: Architecture overviews, setup instructions, best practices
  • Reference Documentation: Configuration options, CLI commands, library APIs
  • Onboarding Materials: Getting started guides, quick starts, installation instructions
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 · 46 lines · 45 tokens per session scan A 9d730b97455a

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 418 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 2026-08-31.