agent-md-refactor

A refactoring guide for large agent instruction files such as AGENTS.md or CLAUDE.md. It organizes essential rules at the top and moves detailed guidance into linked files.

In plain words
What is it for?
Use it to analyze, split, categorize, restructure, and prune an oversized agent configuration file.
Why use it?
It makes instructions easier for coding agents and people to find, while exposing contradictions, repetition, and unclear rules that can cause inconsistent behavior.

Skill for Claude CodeCodex

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 skills/softaworks/agent-toolkit/agent-md-refactor
Any agent
npx skills add softaworks/agent-toolkit --skill agent-md-refactor
Clone the repo
git clone --depth 1 https://github.com/softaworks/agent-toolkit

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00040 $0.01782
Opus 5 $0.00020 $0.00891
Sonnet 5 $0.00008 $0.00356
Haiku 4.5 $0.00004 $0.00178

Measured yesterday against content hash f20e68b59875, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-md-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 yesterday.

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.

Origin

This is a copy

100% identical to agent-md-refactor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agent-md-refactor/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent MD Refactor

Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files.


Triggers

Use this skill when:

  • "refactor my AGENTS.md" / "refactor my CLAUDE.md"
  • "split my agent instructions"
  • "organize my CLAUDE.md file"
  • "my AGENTS.md is too long"
  • "progressive disclosure for my instructions"
  • "clean up my agent config"

Quick Reference

Phase Action Output
1. Analyze Find contradictions List of conflicts to resolve
2. Extract Identify essentials Core instructions for root file
3. Categorize Group remaining instructions Logical categories
4. Structure Create file hierarchy Root + linked files
5. Prune Flag for deletion Redundant/vague instructions

Process

Phase 1: Find Contradictions

Identify any instructions that conflict with each other.

Look for:

  • Contradictory style guidelines (e.g., "use semicolons" vs "no semicolons")
  • Conflicting workflow instructions
  • Incompatible tool preferences
  • Mutually exclusive patterns

For each contradiction found:

## Contradiction Found

**Instruction A:** [quote]
**Instruction B:** [quote]

**Question:** Which should take precedence, or should both be conditional?

Ask the user to resolve before proceeding.


Phase 2: Identify the Essentials

Extract ONLY what belongs in the root agent file. The root should be minimal - information that applies to every single task.

Essential content (keep in root):

Category Example
Project description One sentence: "A React dashboard for analytics"
Package manager Only if not npm (e.g., "Uses pnpm")
Non-standard commands Custom build/test/typecheck commands
Critical overrides Things that MUST override defaults
Universal rules Applies to 100% of tasks

Read the full file on GitHub · 288 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 288 lines · 40 tokens per session scan A f20e68b59875

Subscribe to this mod's changes

agent-md-refactor is a skill published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 1,782 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-md-refactor, differing in 0 lines, and is treated as a copy.