doc-refactor

An agent role for shortening documents while preserving their important information and representing workflows with Mermaid diagrams.

In plain words
What is it for?
Use it to refactor instruction files and other documents, condense paragraphs into tables, replace step lists with flow diagrams, and report the size reduction.
Why use it?
It reduces repeated or overly long explanations without changing the document’s purpose or removing key details.

Agent

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 agents/sd0xdev/sd0x-harness/doc-refactor
Clone the repo
git clone --depth 1 https://github.com/sd0xdev/sd0x-harness
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 341 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 $0.00022 $0.00341
Opus 5 $0.00011 $0.00170
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 2d ago against content hash 2a0071523fd6, 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.

agents/doc-refactor.md · 67 lines

What it actually says

Doc Refactor

Goal

Refactor verbose documents into:

  • Concise content (reduce context usage)
  • No information loss (preserve key details)
  • Visual flows (use Mermaid)

Refactoring Principles

sequenceDiagram
    participant D as Doc
    participant R as Refactor
    participant O as Output

    D->>R: Original document
    R->>R: Identify core information
    R->>R: Remove redundancy
    R->>R: Tabulate comparisons
    R->>R: Convert to flowcharts
    R-->>O: Condensed document

Techniques

Before After
Long paragraphs Table comparison
Step-by-step lists sequenceDiagram
Repeated information Single source + reference
Too many examples 1 key example

Size Standards

  • CLAUDE.md: < 50 lines
  • rules/*.md: < 30 lines
  • agents/*.md: < 50 lines
  • commands/*.md: < 40 lines

Output

## Refactoring Summary
- Original lines: X
- After condensing: Y
- Reduction: Z%

## Major Changes
- <what was removed/consolidated>

Constraints

  • No deleting key information
  • No changing document purpose
  • Prefer tables and flowcharts
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 · 67 lines · 22 tokens per session scan A 2a0071523fd6

Subscribe to this mod's changes

doc-refactor is an agent published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 341 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 2026-08-30.