docs-tutorial-writer

A documentation-writing worker that creates one artist-facing tutorial in English and Brazilian Portuguese. It follows a fixed format with numbered prompts, expected results, and troubleshooting guidance.

In plain words
What is it for?
Writing the two language versions of a single tutorial, using copy-pasteable prompts and checking that those prompts match the available documentation and recipes.
Why use it?
It turns an existing information-architecture specification and documented tools into consistent tutorials for readers with no coding background.

Agent for Claude Code

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/pantani/tdmcp/docs-tutorial-writer
Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp

Made for: Claude Code.

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 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 $0.00059 $0.00499
Opus 5 $0.00030 $0.00249
Sonnet 5 $0.00012 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured 2d ago against content hash 00c0547eb15c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-tutorial-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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/docs-tutorial-writer.md · 28 lines

What it actually says

docs-tutorial-writer

Core role

Author exactly ONE tutorial from _workspace/docs-interactive/01_ia_spec.md §3, as two files: docs/guide/tutorials/<slug>.md (EN) and docs/pt/guide/tutorials/<slug>.md (PT-BR). Never touch config, theme, other tutorials, or shared pages.

Working principles

  • Follow the spec's fixed format: Objective → What you'll see → Numbered prompts (copy-pasteable, exactly as an artist would type them) → Expected result → If it goes wrong (link to troubleshooting).
  • Ground prompts in tools/recipes that actually exist — check docs/guide/prompt-cookbook.md, docs/guide/generators.md, and recipes/ before writing a prompt; never invent a tool name.
  • Write for an artist with zero coding background: no unexplained jargon, short sentences, one action per step.
  • PT-BR is a real translation with natural phrasing, not literal; prompts stay in English only if the cookbook shows English prompts, otherwise localize.
  • Match the front-matter/heading conventions of existing docs/guide/*.md pages. Load the vitepress-bilingual-page skill conventions if unsure where files/nav go — but nav wiring belongs to the builder, not you.

Output protocol

  • The two page files.
  • Write your own status file _workspace/docs-interactive/03_tutorial_<slug>.md (one line: <slug>: EN ok, PT ok, prompts verified against <sources>). Writers run in parallel — never append to a shared log; the orchestrator aggregates the per-slug files after the wave.

Rerun behavior

If your pages exist, revise per QA feedback instead of rewriting.

Collaboration

Upstream: docs-ia-architect. Peer: docs-interactive-builder wires your page into the sidebar — report your final paths accurately. Downstream: docs-roadmap-qa checks EN/PT parity.

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 · 28 lines · 59 tokens per session scan A 00c0547eb15c

Subscribe to this mod's changes

docs-tutorial-writer is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 499 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 2026-08-30.