What is refactor-claude-md?

A maintenance guide for shortening CLAUDE.md, the instruction file used by Claude Code, by moving directory-specific guidance into separate documents and rules. It also describes how to keep the project's specification index consistent.

It helps reorganize agent instructions, compare shared guidance in AGENTS.md, create path-specific rules, and update the related project index and decision records.

Long instruction files are harder to maintain and may load guidance when it is not relevant. This process reduces duplication while preserving the rules agents need.

How statecrafting/spec-spine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to statecrafting/spec-spine. 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/statecrafting/spec-spine/main/.claude/skills/refactor-claude-md/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/statecrafting/spec-spine

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/skills/statecrafting/spec-spine/refactor-claude-md/github.svg)](https://agentmods.dev/skills/statecrafting/spec-spine/refactor-claude-md)

Your own site

<a href="https://agentmods.dev/skills/statecrafting/spec-spine/refactor-claude-md"><img src="https://agentmods.dev/badge/skills/statecrafting/spec-spine/refactor-claude-md/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/skills/statecrafting/spec-spine/refactor-claude-md"><img src="https://agentmods.dev/badge/skills/statecrafting/spec-spine/refactor-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 840 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00043	$0.00840
Opus 5	$0.00022	$0.00420
Sonnet 5	$0.00009	$0.00168
Haiku 4.5	$0.00004	$0.00084

Measured yesterday against content hash 75c2d9874010, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

refactor-claude-md 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.

.claude/skills/refactor-claude-md/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor CLAUDE.md

Reduce the size of CLAUDE.md while preserving guidance, by moving context-specific sections into docs/ and loading them through path-scoped rules. In a spec-spine repository CLAUDE.md, .claude/rules/, and AGENTS.md are usually hashed inputs of the codebase index and owned by a harness spec: every change here couples to that spec (a dated decision entry naming the extraction) and stales the index until spec-spine index runs. Find the owner first:

spec-spine index coverage        # which spec claims the harness files

Process

Read and analyze the current CLAUDE.md in full. Compare it with AGENTS.md: anything duplicated between them belongs in AGENTS.md only (it is the cross-agent authority; CLAUDE.md carries only what Claude Code needs beyond it).
Identify extraction candidates: sections that are cross-cutting patterns rather than core setup, specific to certain directories or file types, long and detailed, or better loaded only when relevant. Typical candidates: per-package implementation notes, testing patterns, a subsystem's conventions, a framework guide.
For each candidate recommend: the doc name under docs/, its scope, the paths: globs that should trigger it, and the one-line reference to keep in CLAUDE.md.
Create the files in this order: extract to docs/<name>.md; create .claude/rules/<name>.md with paths: frontmatter and a short reminder pointing at the doc; replace the extracted section in CLAUDE.md with the reference; update any documentation table.

Path-scoped rule format (the key is paths, a YAML list of globs):
```
---
paths:
  - "crates/<name>/**"
  - "apps/<name>/**"
---

Two or three key points, and the doc to read: `docs/<name>.md`.
```
Couple the change: add a dated decision entry to the harness spec naming the extraction (a new rule file is establishes growth for that spec if it lists rules individually), then spec-spine compile && spec-spine index and stage the derived directory.

Read the full file on GitHub · 93 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.

yesterday First seen · 93 lines · 43 tokens per session scan A 75c2d9874010

Subscribe to this mod's changes

refactor-claude-md is a skill published in the GitHub repository statecrafting/spec-spine (10 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 840 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 2026-09-07.

Building agents Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

spec-spine: Skill for Claude Code