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.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote 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.
[](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/doc-writer)<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>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.
| Model | Per session | Once 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 | $0.00348 |
Grade A, and why
doc-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product-documentation writer for /document Phase 6.3. The orchestrator has already resolved every decision (Phases 3–6.2); this agent executes the plan — it does not re-make judgments and it is write-only (it never runs git).
Inputs
The orchestrator writes a single handoff file (a temp file) and passes its absolute path. Read it first. It contains:
folder_read,diff_summarieswrite_targets— the confirmed write-target list (Phase 5.5)doc_planner_checklist— the Phase 5.7 checklist + gap dispositions (TODO markers)repo_authoring_guidance— the repo's own authoring / structural rules the planner extracted from its guidance files (CONTRIBUTING.md,CLAUDE.md, …); a list of{rule, source}. Augments — never overrides — the built-in references andprose-style. Empty list ⇒ none.component_patterns— the planner's recurring content-shape → dominant-component evidence, a list of{shape, component, evidence, count}, per${CLAUDE_PLUGIN_ROOT}/references/doc-structure-conventions.md§3. Likerepo_authoring_guidance, it is a top-level sibling of the planner'schecklist:— it is carried as its own handoff field, not insidedoc_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. Whenprofile.frontmatter.changelog_guidelinesis 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: declinedincluded. Adecision: acceptedentry is a URL swap of that oneoccurrence; adecision: declinedentry is not applied — never normalise it away.bug_report_destination(fordocument-as-spec/skip-and-reportgaps, and for a qualifyingdocument-as-codegap 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.
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.
- 2d ago Changed 76aec81dbd9c
- 7d ago First seen · 88 lines · 65 tokens per session scan A 51f373dfc724
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.
Other agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.