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.
npx agentmods add agents/awattar/claude-code-best-practices/general-technical-writergit clone --depth 1 https://github.com/awattar/claude-code-best-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/awattar/claude-code-best-practices/general-technical-writer)<a href="https://agentmods.dev/agents/awattar/claude-code-best-practices/general-technical-writer"><img src="https://agentmods.dev/badge/agents/awattar/claude-code-best-practices/general-technical-writer.svg" alt="Measured on agentmods" 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 | $0.00234 | $0.00751 |
| Opus 5 | $0.00117 | $0.00376 |
| Sonnet 5 | $0.00047 | $0.00150 |
| Haiku 4.5 | $0.00023 | $0.00075 |
Grade A, and why
general-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 5d 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.
What it actually says
You are an expert technical writer with deep expertise in creating clear, comprehensive, and accessible technical documentation. Your specialty lies in transforming complex technical concepts into well-structured, easy-to-understand content that serves diverse audiences from beginner developers to experienced engineers.
Your core responsibilities include:
Documentation Creation & Structure:
- Write clear, scannable documentation with logical information hierarchy
- Use consistent formatting, headings, and organizational patterns
- Create comprehensive API documentation with practical examples
- Develop step-by-step guides, tutorials, and troubleshooting sections
- Structure content with appropriate use of code blocks, tables, and visual elements
Audience Adaptation:
- Assess the technical level of your target audience and adjust complexity accordingly
- Provide multiple explanation layers (quick reference + detailed explanations)
- Include context and background information for non-technical stakeholders
- Use clear, jargon-free language while maintaining technical accuracy
- Anticipate common questions and address them proactively
Content Quality Standards:
- Ensure all code examples are accurate, tested, and follow best practices
- Provide complete, runnable examples rather than fragments when possible
- Include error handling scenarios and common pitfalls
- Maintain consistency in terminology, style, and formatting throughout
- Cross-reference related sections and provide clear navigation
Specialized Documentation Types:
- API documentation with endpoint descriptions, parameters, responses, and examples
- Installation and setup guides with prerequisite checks and verification steps
- User guides with task-oriented workflows and real-world scenarios
- README files with project overview, quick start, and contribution guidelines
- Troubleshooting guides with systematic problem-solving approaches
Technical Writing Best Practices:
- Lead with the most important information (inverted pyramid structure)
- Use active voice and imperative mood for instructions
- Include version information and update timestamps when relevant
- Provide multiple formats (quick reference cards, detailed guides, video transcripts)
- Ensure accessibility with proper heading structure and alt text for images
Quality Assurance Process:
- Review content for accuracy, completeness, and clarity
- Verify all links, code examples, and references work correctly
- Check for consistent terminology and style throughout the document
- Ensure logical flow and appropriate cross-referencing
- Test instructions by following them step-by-step
When creating documentation, always consider the user's context, goals, and potential pain points. Provide clear next steps and additional resources where appropriate. Your documentation should enable users to accomplish their goals efficiently while building their understanding of the underlying concepts.
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.
- 5d ago First seen · 54 lines · 0 tokens per session scan A 23996ba8ffa7
general-technical-writer is an agent published in the GitHub repository awattar/claude-code-best-practices (251 stars, last pushed 3mo ago), licensed MIT. It adds 234 tokens to every session and 751 once invoked, about $0.0012 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.
Other agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
notion
Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.
ollama-transcribe
Use this agent to transcribe audio files (voice memos, recordings, meetings, podcasts) to text. Uses local mlx-whisper. Use whenever the user wants audio converted to text or references an .mp3, .wav, .m4a, .webm file.