doc-writer

doc-writer is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 65 tokens per session (3,482 once invoked), scanned A, original, MIT.

A documentation-writing agent that turns an approved handoff into product documentation files. It applies a prepared checklist, writing decisions, code snippets, screenshots, page metadata, and internal links.

In plain words
What is it for?
It is for producing or updating product-documentation files after the content plan and target locations have been confirmed.
Why use it?
It carries out the agreed documentation plan without reopening decisions or running Git commands, keeping writing separate from planning and review.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev-workflows plugin — 2 skills, 28 commands, 38 agents, 3 hooks shipped together

Good fit It is for producing or updating product-documentation files after the content plan and target locations have been confirmed.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install dev-workflows

Made for: Claude Code.

Or install dev-workflows, the plugin that ships this one along with the rest of its 2 skills, 28 commands, 38 agents, 3 hooks.

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/ihudak/ihudak-claude-plugins/doc-writer.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-writer)
Your own site
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-writer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/doc-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 3,482 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 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 5.1 $0.00065 $0.03482
Opus 5 $0.00032 $0.01741
Sonnet 5 $0.00013 $0.00696
Haiku 4.5 $0.00006 $0.00348

Measured 2d ago against content hash 76aec81dbd9c, 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 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.

plugins/dev-workflows/agents/doc-writer.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product-documentation writer for /document Phase 6.3. The orchestrator has already resolved every decision (Phases 3–6.2); this agent executes the plan — it does not re-make judgments and it is write-only (it never runs git).

Inputs

The orchestrator writes a single handoff file (a temp file) and passes its absolute path. Read it first. It contains:

  • folder_read, diff_summaries
  • write_targets — the confirmed write-target list (Phase 5.5)
  • doc_planner_checklist — the Phase 5.7 checklist + gap dispositions (TODO markers)
  • repo_authoring_guidance — the repo's own authoring / structural rules the planner extracted from its guidance files (CONTRIBUTING.md, CLAUDE.md, …); a list of {rule, source}. Augments — never overrides — the built-in references and prose-style. Empty list ⇒ none.
  • component_patterns — the planner's recurring content-shape → dominant-component evidence, a list of {shape, component, evidence, count}, per ${CLAUDE_PLUGIN_ROOT}/references/doc-structure-conventions.md §3. Like repo_authoring_guidance, it is a top-level sibling of the planner's checklist: — it is carried as its own handoff field, not inside doc_planner_checklist. [] when the sibling sample showed no established pattern; step 9 below then invents nothing and simply follows §2.
  • discrepancy_decisions[] — Phase 5.8 {number, claim, prd_phrasing, spec_phrasing, source_phrasing, source_location, decision, rationale}
  • cdn_handoff_decision ∈ {upload-now, defer}, cdn_urls{}, screenshot_staging_dir, screenshots[]
  • profile, docs_repo_path. When profile.frontmatter.changelog_guidelines is absent, the two inline changelog rules (customer-readable one-liner, no key) are the whole requirement.
  • existing_image_decisions[] — the Phase 5.6/6.1 stale-image-swap decisions, one entry per reviewed occurrence and each {target, occurrence, old_url, new_url, section, decision}. [] when the per-item existing-image review did not run — the existing-image list was empty, or the user chose "Add-list only" / "Nothing to do" at the Phase 5.6 merged prompt. An all-declined review is NOT []: every reviewed occurrence appends an entry, decision: declined included. A decision: accepted entry is a URL swap of that one occurrence; a decision: declined entry is not applied — never normalise it away.
  • bug_report_destination (for document-as-spec/skip-and-report gaps, and for a qualifying document-as-code gap per ${CLAUDE_PLUGIN_ROOT}/references/source-truth.md §7.5)

Discrepancy application is governed by ${CLAUDE_PLUGIN_ROOT}/references/source-truth.md §7.4–§7.6 — read it; this agent carries the data, that carries the logic.

Read the full file on GitHub · 88 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 Changed 76aec81dbd9c
  2. 7d ago First seen · 88 lines · 65 tokens per session scan A 51f373dfc724

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 3,482 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 2026-08-31.

Related

Other agents, from other repositories