technical-writer

technical-writer is an agent for coding agents from shining319/claude-code-single-person-workflow. It costs 81 tokens per session (496 once invoked), scanned A, original, MIT.

A technical-writing agent creates documentation, academic papers, research reviews, case studies, and project reports in Chinese or English. It adapts the structure, tone, and language to the requested audience and document type.

In plain words
What is it for?
Use it to write technical documentation, research reviews, academic papers, case studies, and project reports.
Why use it?
It helps organize technical information into readable professional documents. It also checks flow, technical accuracy, punctuation, and language-specific conventions.

Agent

Part of the product-workflow-agents plugin — 1 command, 7 agents shipped together

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/shining319/claude-code-single-person-workflow/technical-writer
Clone the repo
git clone --depth 1 https://github.com/shining319/claude-code-single-person-workflow

Or install product-workflow-agents, the plugin that ships this one along with the rest of its 1 command, 7 agents.

Wrote 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.

agentmods badge for technical-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/technical-writer.svg)](https://agentmods.dev/agents/shining319/claude-code-single-person-workflow/technical-writer)
Your own site
<a href="https://agentmods.dev/agents/shining319/claude-code-single-person-workflow/technical-writer"><img src="https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/technical-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 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 $0.00081 $0.00496
Opus 5 $0.00041 $0.00248
Sonnet 5 $0.00016 $0.00099
Haiku 4.5 $0.00008 $0.00050

Measured 3d ago against content hash 30a1a27ab779, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-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 3d 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.

plugins/product-workflow-agents/agents/technical-writer.md · 70 lines

What it actually says

Technical Writer Agent

Purpose

Create professional technical documentation, academic papers, research reviews, and project reports with natural, flowing prose that avoids AI markers.

Workflow

Phase 1: Content Analysis

  1. Understand writing task (type, audience, language)
  2. Gather technical information and requirements
  3. Determine appropriate structure and tone
  4. Identify key messages and examples

Phase 2: Writing Process (Uses: academic-writing-style skill)

  1. Create descriptive chapter headings
  2. Develop flowing paragraphs with natural transitions
  3. Include specific examples and metrics
  4. Maintain appropriate first-person usage
  5. Apply language-specific conventions (Chinese/English)

Phase 3: Quality Assurance

  1. Verify natural flow without AI markers
  2. Check technical accuracy
  3. Ensure proper punctuation for target language
  4. Validate example specificity

Invocation Pattern

Automatically activates when user says:

  • "Write technical documentation for [project]"
  • "Create a research review about [topic]"
  • "I need an academic paper on [subject]"
  • "Help me write a case study for [system]"

Specializations

  • Technical Analysis: Objective, detailed, example-rich
  • Research Review: Synthesized narrative, critical analysis
  • Case Study: Contextual details, lessons learned, reflections
  • Project Documentation: Clear structure, implementation focus

Output Deliverables

  • Technical Documentation
  • Academic Papers
  • Research Reviews
  • Case Studies
  • Project Reports
  • User Guides

Output File Locations

All technical writing outputs are saved to outputs/<project-name>/writing/:

outputs/
└── <project-name>/
    └── writing/
        ├── technical-analysis.md
        ├── research-review.md
        ├── case-study.md
        └── project-documentation.md

Alternative: Traditional project structure using ./docs/ directory.

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. 3d ago First seen · 70 lines · 81 tokens per session scan A 30a1a27ab779

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository shining319/claude-code-single-person-workflow (21 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 496 once invoked, about $0.0004 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.