write-rules

write-rules is a skill for Claude Code, Codex from YoungjaeDev/my-claude-plugins. It costs 123 tokens per session (4,801 once invoked), scanned B, original, MIT.

A workflow for organizing Claude Code project instructions into a main CLAUDE.md file and optional topic-specific rule files. It checks the project's current instruction layout before changing it.

In plain words
What is it for?
Use it when starting project rules, shortening a large CLAUDE.md, splitting it into .claude/rules files, or reorganizing existing rules.
Why use it?
It helps keep instructions readable and prevents one oversized file from becoming difficult to maintain or apply to the right files.

Skill for Claude CodeCodex

Part of the docs-forge plugin — 11 skills, 3 commands 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 skills/youngjaedev/my-claude-plugins/write-rules
Any agent
npx skills add YoungjaeDev/my-claude-plugins --skill write-rules
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code, Codex.

Or install docs-forge, the plugin that ships this one along with the rest of its 11 skills, 3 commands.

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.

agentmods badge for write-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/write-rules.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/write-rules)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/write-rules"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/write-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00123 $0.04801
Opus 5 $0.00062 $0.02400
Sonnet 5 $0.00025 $0.00960
Haiku 4.5 $0.00012 $0.00480

Measured 3d ago against content hash 003efc24d23b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

write-rules 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 3d 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' -exec wc -l {} + # each ≤150
plugins/docs-forge/skills/write-rules/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Rules

Role

AI Context Architect for CLAUDE.md systems. Scans the project state, detects which of four operating modes applies (NEW / TIGHTEN / SPLIT / REORGANIZE), confirms with the user via AskUserQuestion, then generates or restructures the rules layout following Claude Code 2026 official patterns: .claude/rules/*.md auto-load with paths: glob scoping, 200-line root CLAUDE.md target, Do/Don't structure, no redundant @import directives.

Output conventions are tuned to the official memory docs (see assets/references/claude-code-memory.md). Adapted templates in assets/templates/ and reference examples in assets/examples/ ground the generation.

Modes

Mode Trigger What it does
NEW CLAUDE.md 부재 인터뷰 → 카테고리 선택 → root + 초기 .claude/rules/*.md 생성
TIGHTEN CLAUDE.md ≤200줄, .claude/rules/ 비어있음 root 만 Do/Don't 로 재구조화 + paths: 후보 제안, 신규 rules 파일 없음
SPLIT CLAUDE.md >200줄, .claude/rules/ 비어있음 섹션 추출 → .claude/rules/<topic>.md 자동 생성, root 축약
REORGANIZE CLAUDE.md + .claude/rules/ 둘 다 존재 root cap 초과·rules 중복·paths: 누락 점검 후 per-file 패치

Detection Logic

Scan project state with Bash, then propose a mode.

state = {
  hasClaudeMd:      exists("./CLAUDE.md") or exists("./.claude/CLAUDE.md")
  claudeMdPath:     "./CLAUDE.md" or "./.claude/CLAUDE.md" (whichever exists)
  claudeMdLines:    wc -l on the file if present
  hasRulesDir:      exists("./.claude/rules/") and contains at least one *.md
  rulesFileCount:   count of .claude/rules/*.md
  hasAgentsMd:      exists("./AGENTS.md")
  contentSignals:   tags derived from grep over root + rules content
                    (clean-arch, nextjs-framework, supabase, service-spec)
}

mode =
  NEW         if not state.hasClaudeMd
  TIGHTEN     if state.hasClaudeMd and state.claudeMdLines <= 200 and not state.hasRulesDir
  SPLIT       if state.hasClaudeMd and state.claudeMdLines > 200 and not state.hasRulesDir
  REORGANIZE  if state.hasClaudeMd and state.hasRulesDir

Read the full file on GitHub · 404 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.

  1. 3d ago First seen · 404 lines · 123 tokens per session scan B 003efc24d23b

Subscribe to this mod's changes

write-rules is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 123 tokens to every session and 4,801 once invoked, about $0.0006 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens