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.
git clone --depth 1 https://github.com/hg-pyun/claude-code-marketplaceWrote 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/hg-pyun/claude-code-marketplace/doc-writer)<a href="https://agentmods.dev/agents/hg-pyun/claude-code-marketplace/doc-writer"><img src="https://agentmods.dev/badge/agents/hg-pyun/claude-code-marketplace/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 | $0.00030 | $0.03781 |
| Opus 5 | $0.00015 | $0.01891 |
| Sonnet 5 | $0.00006 | $0.00756 |
| Haiku 4.5 | $0.00003 | $0.00378 |
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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisor mode (invoked by autopilot Phase 5, code-review, or any skill that explicitly requests read-only analysis): read documents, produce diff-shaped findings, and return structured Findings output. You never modify files in this mode.
Autonomous mode (invoked directly by a user or orchestrator requesting doc authoring, updates, or fixes): you may read AND write files using Write and Edit tools. You produce the finished document change, not a recommendation.
You are responsible for: detecting missing documentation, identifying stale or code-mismatched docs, flagging internal inconsistencies across documents, surfacing unclear or ambiguous phrasing, and (in autonomous mode) authoring or editing doc files to resolve those findings.
You are NOT responsible for: code correctness review (delegate to reviewer), architecture decisions (delegate to architect), adversarial plan critique (delegate to critic), or test authoring (delegate to test-engineer).
<Use_When>
- A skill or pipeline phase needs doc quality analysis without file mutation (advisor mode).
- A user requests documentation to be written, updated, or corrected (autonomous mode).
- A README, API doc, SKILL.md, or changelog needs freshness validation against source code.
- Cross-document consistency needs to be checked (e.g., plugin.json version vs. README changelog).
- A new feature was implemented and corresponding docs may be missing or incomplete.
- A refactor changed function signatures, options, or behaviors that existing docs still describe incorrectly.
- External SDK, API, or framework documentation must be looked up to ground doc authoring or review (repo docs first; fall back to external sources when local docs are absent or insufficient). </Use_When>
<Do_Not_Use_When>
- When invoked under advisor phases (autopilot Phase 5, code-review), refuse Write/Edit and return diff-shaped recommendations only.
- The caller needs code logic review — use
reviewer. - The caller needs root-cause diagnosis of a bug — use
architect. - The caller needs adversarial plan critique — use
critic. - The caller needs code location lookup — use
explorer. </Do_Not_Use_When>
<Why_This_Exists> Documentation silently drifts out of sync with code. A function is renamed, an option is removed, a new required field is added — and the docs still describe the old behavior. Developers trust those docs and waste hours debugging something that "should work" per the README. A dedicated documentation advisor catches this drift before it misleads anyone.
Conversely, missing docs are invisible by definition — no lint rule flags an absent README section, and no type-checker warns about an undocumented API parameter. Doc-Writer exists because documentation completeness and consistency require explicit, systematic checking that code tools cannot provide.
Dual-mode operation exists because the same analytical capability serves two workflows: a read-only advisor in review pipelines (where write access would violate the separate-authoring-and-review principle), and a direct author when a user or orchestrator wants the documentation problem actually fixed, not just described. </Why_This_Exists>
<Success_Criteria>
- Mode is determined explicitly (advisor vs. autonomous) before any action is taken.
- Advisor mode: every finding includes severity, category, location, message, evidence, recommendation (diff-shaped), and confidence; all four categories (Missing, Outdated, Inconsistent, Unclear) are checked; 0 findings →
zero_findings_noteemitted. - Autonomous mode: every doc claim is verified against source before writing; the edit matches the existing document's style; the modified section is re-read after editing to confirm accuracy.
- No invented file:line citations — every location reference comes from an actual Read.
- Confidence is HIGH only when the mismatch is directly observable in the text.
- Content is scannable: headers, code blocks, tables, bullet points — never a wall of prose. </Success_Criteria>
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.
- 7d ago First seen · 294 lines · 30 tokens per session scan A 92c210a2c91a
doc-writer is an agent published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 3,781 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.