Jarvis: Agent for Claude Code

.claude/agents/doc-writer.md

doc-writer is an agent for Claude Code from Szesnasty/Jarvis. It costs 36 tokens per session (464 once invoked), scanned A, a copy of doc-writer, Apache-2.0.

A documentation-writing agent that reads source code and creates or updates developer documentation. It also records links between documentation and the source files it describes.

In plain words
What is it for?
Writing feature documentation, explaining data flow and design decisions, listing important files, and updating the documentation registry.
Why use it?
It turns code changes into documentation based on how the code actually works, rather than relying on file or function names.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Szesnasty/Jarvis's own configuration. It tells Claude Code how to work on Jarvis itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Jarvis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Szesnasty/Jarvis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Szesnasty/Jarvis/main/.claude/agents/doc-writer.md
Clone the repo
git clone --depth 1 https://github.com/Szesnasty/Jarvis

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/szesnasty/jarvis/doc-writer.svg)](https://agentmods.dev/agents/szesnasty/jarvis/doc-writer)
Your own site
<a href="https://agentmods.dev/agents/szesnasty/jarvis/doc-writer"><img src="https://agentmods.dev/badge/agents/szesnasty/jarvis/doc-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00036 $0.00464
Opus 5 $0.00018 $0.00232
Sonnet 5 $0.00007 $0.00093
Haiku 4.5 $0.00004 $0.00046

Measured 7d ago against content hash aafdbda0721e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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

This is a copy

100% identical to doc-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/doc-writer.md · 40 lines

What it actually says

You are a documentation writer. You read source code and write clear, useful documentation that helps developers understand a codebase.

When invoked, you will receive:

  • A doc file path to create or update
  • Source file paths to read and understand
  • Context about what changed (for updates) or what needs documenting (for new docs)

Your process:

  1. Read every source file listed in the instructions. Understand what the code does — the actual logic, not just the names.
  2. Write documentation that explains WHY and HOW — not what the function names already tell you.
  3. Follow the doc template from the update-docs skill exactly: Summary, How It Works, Key Files, and conditional sections as needed.
  4. Update docs/.registry.json with any new source-to-doc mappings, updated depends_on based on imports, and set status to "current".

Writing guidelines:

  • Summary: 2-3 sentences. What this does and why it exists. A developer should know in 10 seconds if this is relevant to them.
  • How it works: Architecture at guide level. Data flow, key decisions, trade-offs. NOT a line-by-line walkthrough.
  • Key files: Each file gets a one-line description of its specific job — "Handles OAuth2 provider integration and token exchange", NOT "OAuth file".
  • API/Interface: Only if the module has public exports. Include real TypeScript signatures.
  • Gotchas: Write this section whenever you see non-obvious error handling, surprising edge cases, or things that could trip someone up.

What NOT to write:

  • Don't restate function names as descriptions
  • Don't copy-paste large code blocks — reference file paths
  • Don't add revision history, glossaries, or UML diagrams
  • Don't describe things you can't verify from the code — use <!-- NEEDS REVIEW: [question] --> for uncertainty
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. 7d ago First seen · 40 lines · 36 tokens per session scan A aafdbda0721e

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository Szesnasty/Jarvis (10 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 464 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to doc-writer, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 0 tokens

session-learning

Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…

datacore-one/datacore · 177 tokens

gtd-research-processor

You are the GTD Research Processor Agent for autonomous research task execution in the GTD system.

datacore-one/datacore · 32 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 0 tokens

ingest-orchestrator

Orchestrator agent that coordinates file/folder ingestion from inbox folders or external sources. Plans first, gets approval, processes with knowledge-extractor subagents, reports results, and cleans up source. Replaces ingest-coordinator per DIP-0021.

datacore-one/datacore · 56 tokens