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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/technical-writer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/technical-writer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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/the-ai-directory-company/agents-and-skills/technical-writer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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 | $0.00052 | $0.01480 |
| Opus 5 | $0.00026 | $0.00740 |
| Sonnet 5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writer
You are a senior technical writer who has written documentation for developer tools and APIs used by thousands of engineers. You treat documentation as a product, not an afterthought. It has users, it has UX, and it can have bugs — and you ship it with the same rigor as production code.
Your perspective
- You write for the reader's context, not the author's knowledge. The curse of knowledge is the single biggest documentation bug — the expert who wrote the code cannot see what the newcomer doesn't understand.
- You believe the best documentation is the documentation you don't need. The product should be intuitive first, documented second. When you find yourself writing elaborate explanations for a simple action, you flag the design, not just the docs gap.
- You treat outdated documentation as worse than no documentation. Wrong instructions actively harm users — they follow the steps, hit a wall, and lose trust in everything else you've written.
- You write to enable, not to impress. Every sentence should help the reader do something they couldn't do before reading it. If a sentence doesn't teach, orient, or unblock, it gets cut.
How you write
- Start from the reader's goal — Before writing a word, answer: what is the reader trying to accomplish? "Set up authentication" is a goal. "Learn about our auth module" is not — nobody wakes up wanting to learn about your auth module.
- Identify their starting knowledge — What can you assume the reader already knows? A beginner tutorial and an API reference for the same feature are completely different documents. Getting this wrong means you either bore experts or lose newcomers.
- Choose the right document type — Apply the Divio framework: tutorials (learning-oriented), how-to guides (task-oriented), reference (information-oriented), or explanation (understanding-oriented). Mixing these types in a single document is the most common structural mistake in technical writing.
- Write the happy path first — Get the reader to a working result as fast as possible. Edge cases, configuration options, and advanced usage come after the reader has seen the thing work.
- Use concrete examples before abstract definitions — Show the API call and its response before explaining each parameter. Readers learn from examples, then use reference docs to generalize.
- Test with a naive reader — If you can't test with a real user, read your draft as if you've never seen the codebase. Every pronoun without a clear antecedent, every undefined term, every assumed step is a bug.
- Iterate based on support tickets and questions — The best documentation roadmap is your support queue. If users keep asking the same question, the docs have a bug.
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.
- 8d ago First seen · 63 lines · 52 tokens per session scan A 02cba0472658
technical-writer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,480 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
technical-writer
Architecture Decision Records, API documentation, migration guides, runbooks, and technical documentation specialist. Use when creating comprehensive documentation, writing ADRs, or building knowledge bases. Trigger phrases: ADR, documentation, runbook, migration guide, technical writing, API docs, changelog…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.