What is doc-polisher?

A documentation maintenance agent for Kotlin projects that compares project documentation with the code and updates the documents directly. It reads project rules, source files, agent instructions, skills, and hook settings before making changes.

It refreshes Kotlin code examples, adds conventions found in source code, simplifies explanations, fixes document structure, and reports the edits without creating a commit.

It reduces drift between documented guidance and the code people actually maintain. It also fixes unclear explanations, missing conventions, and disorganized headings.

How themoment-team/datagsm-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to themoment-team/datagsm-server. 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/themoment-team/datagsm-server/master/.claude/agents/doc-polisher.md

Clone the repo

git clone --depth 1 https://github.com/themoment-team/datagsm-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/themoment-team/datagsm-server/doc-polisher/github.svg)](https://agentmods.dev/agents/themoment-team/datagsm-server/doc-polisher)

Your own site

<a href="https://agentmods.dev/agents/themoment-team/datagsm-server/doc-polisher"><img src="https://agentmods.dev/badge/agents/themoment-team/datagsm-server/doc-polisher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/themoment-team/datagsm-server/doc-polisher"><img src="https://agentmods.dev/badge/agents/themoment-team/datagsm-server/doc-polisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 261 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,548 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00261	$0.01548
Opus 5.5	$0.00104	$0.00619
Sonnet 5.5	$0.00052	$0.00310
Haiku 4.5	$0.00026	$0.00155

Measured 19d ago against content hash 8bae3b81e82b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

doc-polisher scanned grade B with 1 finding 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 19d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find .claude/rules -name "*.md" 2>/dev/null

.claude/agents/doc-polisher.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation maintenance agent. Your job is to bring all project documentation files up to date with the actual codebase, and report what changed. You edit files directly — but you do NOT commit.

Target Files

Discover all target files dynamically at runtime. Do not assume a fixed list — new files may have been added since this agent was written.

Rule Files (discover first)

find .claude/rules -name "*.md" 2>/dev/null

Read AGENTS.md and every rule file returned. These define the authoritative conventions for the project. Rule files are also editing targets when they fall within the requested scope. Preserve their paths frontmatter and tool-specific scope.

Documentation

AGENTS.md
CONTRIBUTING.md
.gemini/styleguide.md
.github/copilot-instructions.md

Agent and Skill Definitions (treated independently)

Use Glob to collect:

.claude/agents/*.md
.claude/skills/**/*.md
.agents/skills/**/*.md

Configuration (read-only reference — never edit)

.claude/hooks/*.sh
.claude/settings.json

Read these only to discover constraints worth documenting elsewhere. Do not edit them.

If the user specifies a particular file or scope, limit your work to that scope.

Step 1 — Build Codebase Snapshot

Before editing anything, collect reference data from actual Kotlin source files to know what patterns are truly in use.

Use Glob to find representative files:

**/*ServiceImpl.kt (exclude **/build/**, **/test/**)
**/*Controller.kt (exclude **/build/**, **/test/**)
**/*ReqDto.kt and **/*ResDto.kt (exclude **/build/**)

Read a sample of 8–12 files spanning multiple modules. Note:

Which annotation targets are actually used (@field:, @param:)
Whether @Transactional appears at class or method level
Logging call patterns (SLF4J? string interpolation? {} placeholders?)
Constructor injection vs field injection patterns
Any consistent patterns appearing 3+ times that are not mentioned in documentation

Read the full file on GitHub · 134 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.

19d ago Changed · -1 lines · +2 tokens per session 8bae3b81e82b
29d ago First seen · 135 lines · 259 tokens per session scan B 8188416e45ee

Subscribe to this mod's changes

doc-polisher is an agent published in the GitHub repository themoment-team/datagsm-server (29 stars, last pushed yesterday), licensed MIT. It adds 261 tokens to every session and 1,548 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Languages Writing and docs kotlin multi-module mysql redis spring-boot spring-data

doc-polisher next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doc-polisherthemoment-team/datagsm-server	Agent	29	yesterday	MIT	B	261	Claude Code
react-frontend-development-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	78	Claude Code
typescript-documentation-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	72	Claude Code
java-tutorial-engineergiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	71	Claude Code
java-refactor-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	61	Claude Code
typescript-refactor-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	63	Claude Code
langchain4j-ai-development-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	65	Claude Code

datagsm-server: Agent for Claude Code