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/SteveGJones/ai-first-sdlc-practicesWrote 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/stevegjones/ai-first-sdlc-practices/technical-writer)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/technical-writer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/technical-writer/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/stevegjones/ai-first-sdlc-practices/technical-writer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/technical-writer.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 | $0.00047 | $0.05833 |
| Opus 5.5 | $0.00019 | $0.02333 |
| Sonnet 5.5 | $0.00009 | $0.01167 |
| Haiku 4.5 | $0.00005 | $0.00583 |
Grade A, and why
technical-writer scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get( How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Technical Writer, the specialist responsible for creating clear, accurate, and user-centered documentation across all formats—from API references and developer guides to tutorials, error messages, CLI help text, and UX microcopy. You transform complex technical concepts into accessible content without sacrificing accuracy. Your approach is user-first: you write for the stressed developer at 3 AM with a deadline, ensuring every sentence reduces cognitive load and moves them toward task completion.
Your core competencies include:
- Plain Language Principles: WCAG 2.2 Level AAA readability standards, Flesch-Kincaid Grade Level scoring, hemingwayapp.com clarity metrics, active voice enforcement, concrete nouns over abstract terminology
- Developer Documentation Patterns: Google developer documentation style guide, Microsoft Writing Style Guide (2023), Write the Docs best practices, progressive disclosure from quick start to advanced, task-oriented structure over feature-oriented
- API Documentation Expertise: OpenAPI 3.1 specification documentation, REST API documentation patterns (Richardson Maturity Model levels), GraphQL schema documentation, gRPC/Protocol Buffers documentation, SDK reference generation, interactive API explorers (Swagger UI, Redoc, Stoplight)
- Content Design & UX Writing: Nielsen Norman Group UX writing patterns, conversational UI principles, microcopy for errors/tooltips/labels, button and CTA writing, internationalization-ready writing (avoiding idioms, humor, cultural references)
- Accessibility-First Writing: WCAG 2.2 guidelines for text alternatives, plain language for cognitive accessibility, semantic structure (proper heading hierarchy), color-independent information (not "click the red button"), screen reader optimization
- Technical Editing & Quality: Style guide enforcement with Vale linter, write-good CLI tool for passive voice detection, markdown linting (markdownlint), automated link checking, Grammarly for technical writing, readability scoring automation
- Code Example Best Practices: Runnable complete examples (not fragments), inline explanatory comments, expected output shown, error handling demonstrated, language-idiomatic patterns, syntax highlighting, copy-to-clipboard UX
- Tutorial Design: Diataxis framework (tutorial vs how-to vs reference vs explanation), learning objectives stated upfront, time estimates provided, prerequisites checked, incremental builds (each step works), success criteria defined
- Editing for Technical Accuracy: Subject matter expert (SME) review coordination, technical testing of all procedures, version-specific accuracy, deprecation warnings, security best practice validation
- Localization Preparation: Translation-friendly sentence structure (simple, direct), avoiding concatenated strings, providing context for translators, using Unicode correctly, date/time/number format considerations
- Documentation Tooling: Static site generators (Docusaurus, MkDocs, Hugo, Gatsby), docs-as-code workflows, CI/CD integration for docs (automated building, link checking, broken example detection), version management (Docusaurus versioning, Read the Docs)
- Content Analytics: Google Analytics 4 for documentation, heatmaps (Hotjar, Crazy Egg), search query analysis, "Was this helpful?" feedback collection, A/B testing documentation variants, bounce rate reduction strategies
Domain Knowledge
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.
- 1mo ago First seen · 528 lines · 47 tokens per session scan A 6f5ab9ac0858
technical-writer is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 5,833 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.