doc-refactor

A command for shortening and reorganizing documentation while keeping its important information. It can turn long explanations into tables, show steps as flow diagrams, and remove repeated content.

In plain words
What is it for?
Use it to refactor files such as CLAUDE.md and other Markdown instructions, check what information was preserved, and compare the original and new line counts.
Why use it?
It reduces the time needed to read and maintain documentation without changing the underlying policy or source meaning.

Command

Part of the dhpk plugin — 19 commands, 36 agents shipped together

Install

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.

agentmods
npx agentmods add commands/hmj1026/dhpk/doc-refactor
Clone the repo
git clone --depth 1 https://github.com/hmj1026/dhpk

Or install dhpk, the plugin that ships this one along with the rest of its 19 commands, 36 agents.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00303
Opus 5 $0.00008 $0.00151
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash 1da28f35b858, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-refactor 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.

commands/doc-refactor.md · 56 lines

What it actually says

Contract

Use for a bounded documentation refactor; not for changing policy or source semantics. See the command contract. Stop when the input is missing or unsafe to rewrite; completion reports the preserved facts, output path, and before/after line counts.

Task

For the file specified by $ARGUMENTS:

  1. Analyze original content

    • Count lines
    • Identify core information vs redundancy
  2. Refactor

    • Long paragraphs -> tables
    • Steps -> sequenceDiagram
    • Duplicates -> single source
  3. Validate

    • Key information preserved
    • Line count reduced

Simplification Standards

File Type Target Lines
CLAUDE.md < 50
rules/*.md < 30
agents/*.md < 50
commands/*.md < 40

Output

## Refactoring Result

- Original: X lines
- Simplified: Y lines (-Z%)

## Changes

- <summary>
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 First seen · 56 lines · 15 tokens per session scan A 1da28f35b858

Subscribe to this mod's changes

doc-refactor is a command published in the GitHub repository hmj1026/dhpk (2 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 303 once invoked, about $0.0001 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.