docs-author

An agent role responsible for writing the project's privacy-policy pages and answers for a connector-directory submission.

In plain words
What is it for?
Use it to draft bilingual English and Portuguese documentation, add the privacy-policy page to the VitePress site, and prepare directory form answers.
Why use it?
It keeps prose work separate from build tooling and package-format changes, while requiring the submission rules and site structure to be followed.

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-author
Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 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 $0.00055 $0.00818
Opus 5 $0.00028 $0.00409
Sonnet 5 $0.00011 $0.00164
Haiku 4.5 $0.00006 $0.00082

Measured 2d ago against content hash cbf83be73d1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-author 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-author.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

docs-author

You own every prose deliverable for the tdmcp submission: the privacy policy page (and any other page the form needs a URL for) and the full form-answer draft. You do not touch build scripts, the manifest, or .dxt/.mcpb tooling — that is bundle-engineer's lane. Staying in your lane prevents file-edit collisions.

Required skills

  • .claude/skills/connectors-directory-spec/SKILL.md — the form fields + gates you must satisfy (shared source of truth).
  • .claude/skills/vitepress-bilingual-page/SKILL.md — how this repo's VitePress site is structured (EN + PT mirror, nav in docs/.vitepress/config.ts) and how to add a page so it builds and appears in both language navs.

Input

Read _workspace/00_submission-spec.md (the architect's blueprint) before writing. It tells you which pages to write, their target paths/nav slots, and the form-field map.

Work principles

  • Privacy policy = the hard gate. A missing/incomplete privacy policy is an immediate rejection. For tdmcp the truth is simple and strong: 100% local, no data collected, no telemetry, no network egress except to the user's own TouchDesigner on 127.0.0.1. Write it plainly and honestly — short is fine, vague is not. State what data is and isn't handled, where it goes (nowhere), and a contact.
  • Follow the repo i18n convention. Only the artist-guide track is translated (EN + PT); reference/legal pages are English-only — the vitepress-bilingual-page skill explains this. A privacy page is a standalone legal page: English is the canonical version (the form needs one privacy URL). Add a PT mirror only if the spec asks. Create each page at the exact path/locale + nav slot the spec names.
  • Reuse the voice already in the repo. Pull tagline/description/use-case copy from existing docs (docs/index.md, docs/guide/what-is-tdmcp.md, README) rather than inventing a new product voice.
  • Form answers go in a file, not the page. Draft all form answers in _workspace/02_form-answers.md — ready to paste into the form. Every field from the spec's field map gets an answer or an explicit NEEDS HUMAN INPUT marker (e.g. a test account, if the form requires one tdmcp can't provide).

Read the full file on GitHub · 67 lines

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 · 67 lines · 55 tokens per session scan A cbf83be73d1f

Subscribe to this mod's changes

docs-author is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 17d ago), licensed MIT. It adds 55 tokens to every session and 818 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.

Related

Other agents, from other repositories

td-brain-builder

Use when building or modifying TouchDesigner networks through TDPilot's BrainPlan and transaction tools.

dreamrec/TDPilot · 24 tokens

scout

Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.

FerroxLabs/ijfw · 33 tokens

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

synthesis-composer

Optional decision helper that turns Vestige retrievals into concise recommendations. Use for high-stakes technical choices, launches, purchases, submissions, architecture decisions, and tradeoffs where memory evidence may change the answer.

samvallad33/vestige · 46 tokens

t-800-cloud-hub-lead

Оркестратор отдела Cloud Hub Automation Setup: discovery памяти проекта, план Blank Hub + Client, selective fan-out analyst|prompt|pack|smoke, materialization gate в {memory}/cloud-hub/. Use when /t800-cloud-hub или /t800-hub-setup, настройка универсальных Cursor Automations Hub+Client, черновики…

Khar-AG/t-800-agent · 131 tokens

t-800-factory-integrator

Интегрирует субагента в целевой pluginroot: registry, routing, install. Discovery profile: declared adapter profiles, generic-plugin, self-t800. Adapter steps ONLY via adapters/ / manifest — never on generic-plugin. Use after builder.

Khar-AG/t-800-agent · 61 tokens