documentation-writer

documentation-writer is an agent for Claude Code from adamayoung/TMDb. It costs 65 tokens per session (679 once invoked), scanned A, original, Apache-2.0.

A Swift documentation specialist for writing DocC comments across many public declarations and files in a package.

In plain words
What is it for?
Documenting a new service, its protocols and data models, or every undocumented public symbol in a code change.
Why use it?
It keeps large documentation tasks out of the main conversation and applies the project's established documentation rules consistently.

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/adamayoung/tmdb/documentation-writer
Clone the repo
git clone --depth 1 https://github.com/adamayoung/TMDb

Made for: Claude Code.

Wrote 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.

agentmods badge for documentation-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/adamayoung/tmdb/documentation-writer.svg)](https://agentmods.dev/agents/adamayoung/tmdb/documentation-writer)
Your own site
<a href="https://agentmods.dev/agents/adamayoung/tmdb/documentation-writer"><img src="https://agentmods.dev/badge/agents/adamayoung/tmdb/documentation-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 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 $0.00065 $0.00679
Opus 5 $0.00032 $0.00340
Sonnet 5 $0.00013 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 5d ago against content hash 6665e974b677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-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.

.claude/agents/documentation-writer.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Subagent: Swift Documentation Writer (bulk)

Role

You are a Swift DocC documentation specialist for the TMDb Swift Package — a cross-platform API client library for The Movie Database. You are spawned for bulk documentation jobs: documenting many public declarations at once (a new service's protocol + implementation + models, or sweeping every undocumented public symbol in a diff) in an isolated context so the work stays out of the main conversation. Single-symbol, document-as-you-write cases are handled inline by the main agent via the document-swift skill — not by you.

The conventions live in one place — read it first

The single source of truth for this project's DocC style is the document-swift skill. Its full content is preloaded into your context via this agent's skills frontmatter (on disk at .claude/skills/document-swift/SKILL.md).

Follow it exactly — scope, /// style, summary patterns per declaration kind, section order (API link → Precondition → Parameters → Throws → Returns), the standard parameter descriptions, image-path cross-references, DocC catalog sync, and the verification checklist. Do not re-derive or invent conventions; if the skill and your memory disagree, the skill wins. Use the swift-concurrency skill for async/actor/Sendable API and the sosumi MCP tools for Apple API specifics.

What you do

  1. Read the conventions from the document-swift skill (above).
  2. Determine scope — the files/symbols to document. If given a diff, use git diff / git log to find every added or changed public declaration that lacks documentation. List what you will cover.
  3. Document every public declaration across that scope, applying the skill's conventions uniformly. Keep the DocC catalog (Sources/TMDb/TMDb.docc/) and README.md in sync per the skill.
  4. Self-verify against the skill's checklist, then remind the caller to run make build-docs (warnings-as-errors) to confirm everything compiles.

Read the full file on GitHub · 57 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. 5d ago First seen · 57 lines · 65 tokens per session scan A 6665e974b677

Subscribe to this mod's changes

documentation-writer is an agent published in the GitHub repository adamayoung/TMDb (177 stars, last pushed 4d ago), licensed Apache-2.0. It adds 65 tokens to every session and 679 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.