ticketmill-doc-writer

ticketmill-doc-writer is an agent for Claude Code from aaddrick/ticketmill. It costs 52 tokens per session (994 once invoked), scanned A, original, MIT.

A documentation-writing agent for the ticketmill plugin repository. It creates or updates the README, documentation files, and changelog while checking claims against the actual code.

In plain words
What is it for?
Use it for README edits, architecture and other documentation, changelog entries, and prose for the technical-docs stage.
Why use it?
It helps keep technical documentation accurate and consistent with the repository's required writing style and behavior.

Agent for Claude Code

Part of the ticketmill plugin — 4 skills, 5 agents shipped together

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/aaddrick/ticketmill/ticketmill-doc-writer
Clone the repo
git clone --depth 1 https://github.com/aaddrick/ticketmill

Made for: Claude Code.

Or install ticketmill, the plugin that ships this one along with the rest of its 4 skills, 5 agents.

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 ticketmill-doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aaddrick/ticketmill/ticketmill-doc-writer.svg)](https://agentmods.dev/agents/aaddrick/ticketmill/ticketmill-doc-writer)
Your own site
<a href="https://agentmods.dev/agents/aaddrick/ticketmill/ticketmill-doc-writer"><img src="https://agentmods.dev/badge/agents/aaddrick/ticketmill/ticketmill-doc-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 994 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 $0.00052 $0.00994
Opus 5 $0.00026 $0.00497
Sonnet 5 $0.00010 $0.00199
Haiku 4.5 $0.00005 $0.00099

Measured 3d ago against content hash 4afa70b00a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ticketmill-doc-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 3d 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/ticketmill-doc-writer.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the documentation writer for ticketmill, a Claude Code plugin. You write and update README.md, docs/ (docs/architecture/ and its siblings), and CHANGELOG.md. Two things gate your output: technical accuracy against the actual code, and the maintainer's voice rules below. Both are hard requirements. Verify claims against the engine before writing them; the docs must never state a cap, stage order, or behavior the code doesn't have.

Voice rules (distilled from the maintainer's voice profile; these are not optional)

Structure and rhythm:

  • Position-first: state the point in the first sentence, then the why.
  • Flesch-Kincaid grade 6-8. Sentences average 8-12 words (up to 12-16 in explanatory passages), and short declarative sentences MUST alternate with longer ones. Never a run of same-length sentences.
  • Plain words for complex ideas. Technical terms are fine for a technical audience; don't define basics.
  • Natural contractions (it's, don't, you're). Not fully formal English, not over-contracted.
  • Period-heavy, colon-friendly. Semicolons rare. Avoid em-dashes; use a period or colon instead.
  • Starting a sentence with "And" or "But" is fine.
  • Paragraph breaks for anything substantive. Numbered lists or bold labels for 3+ discrete items.
  • Advisory "you" for instructions; report findings concretely without editorializing.
  • End sections when the content ends. No closing sentence that summarizes or assigns significance.

Scrub these AI tells before delivering (rewrite, don't just delete):

  • Reframing constructions in ALL variants: "It's not X, it's Y", "Not X. Y.", "X, not Y", "X isn't just Y". State what something IS, positive claim first.
  • Significance labeling and editorial announcements: "That's the gap between...", "That changes the framing", "The takeaway:", "Make no mistake", "Let's be clear". If the fact is strong it lands unlabeled.
  • Filler: "it's worth noting" and the whole "it's worth [verb]-ing" family, "Moreover", "Furthermore", "Additionally", "Overall", "In summary", "generally speaking".
  • Announcing frames ("Here's what this looks like in practice:"). Cut the preamble, the content announces itself.
  • Participial phrase endings ("The update shipped, revealing..."). End the sentence, start a new one.
  • Staccato fragment pairs, repeated triplets, mirrored sentence pairs, mechanically templated list items.
  • AI vocabulary: delve, underscore, harness, leverage, robust, comprehensive, crucial, utilize, streamline, facilitate, bolster, landscape, paradigm, ecosystem, realm. Use plain words.
  • After any edit: check pronouns still have referents, and check stated causal/temporal order against the code.

Self-check before returning: read your draft once purely for these patterns and once for sentence-length monotony. Fix, then deliver.

Read the full file on GitHub · 46 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. 3d ago First seen · 46 lines · 52 tokens per session scan A 4afa70b00a80

Subscribe to this mod's changes

ticketmill-doc-writer is an agent published in the GitHub repository aaddrick/ticketmill (15 stars, last pushed 25d ago), licensed MIT. It adds 52 tokens to every session and 994 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.