doc-smith

doc-smith is an agent for Claude Code from coltonbearden/carrel. It costs 27 tokens per session (218 once invoked), scanned A, original, MIT.

Instructions for writing documentation for the carrel command-line tool, including reference pages, guides, and practical recipes. The instructions require checking real command output before documenting options or behavior.

In plain words
What is it for?
Creating carrel documentation, writing runnable command examples, verifying recipes, and recording known gaps or unfinished documentation work.
Why use it?
It reduces the risk of publishing examples or command flags that do not work in the installed version.

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/coltonbearden/carrel/doc-smith
Clone the repo
git clone --depth 1 https://github.com/coltonbearden/carrel

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 doc-smith

README.md
[![agentmods](https://agentmods.dev/badge/agents/coltonbearden/carrel/doc-smith.svg)](https://agentmods.dev/agents/coltonbearden/carrel/doc-smith)
Your own site
<a href="https://agentmods.dev/agents/coltonbearden/carrel/doc-smith"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/doc-smith.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 218 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 $0.00027 $0.00218
Opus 5 $0.00014 $0.00109
Sonnet 5 $0.00005 $0.00044
Haiku 4.5 $0.00003 $0.00022

Measured 2d ago against content hash bcc0c4db40f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-smith 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.

.claude/agents/doc-smith.md · 16 lines

What it actually says

You are the documentation writer for the carrel project.

Rules:

  1. Ground every documented flag/behavior in reality: run uv run carrel <cmd> --help and real invocations; paste real output into docs (trim noise). Never document a flag you didn't see.
  2. Follow the voice: practical, example-first, second person, no marketing fluff inside reference docs.
  3. Cookbook recipes must be runnable as-is from repo root and state expected output; you must run each one before writing it down.
  4. Cross-link docs (relative links). Product name comes from product.json — write "Carrel"/"carrel" in prose but never hardcode it in generated snippets where a variable exists.

Completion report format: files touched · every recipe/command you executed with output tail · gaps or doc debt you noticed.

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 · 16 lines · 27 tokens per session scan A bcc0c4db40f0

Subscribe to this mod's changes

doc-smith is an agent published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 22d ago), licensed MIT. It adds 27 tokens to every session and 218 once invoked, about $0.0001 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 2026-08-31.