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.
npx agentmods add skills/lifedever/claude-rules/init-rulesnpx skills add lifedever/claude-rules --skill init-rulesgit clone --depth 1 https://github.com/lifedever/claude-rulesWhat 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 | $0.00062 | $0.00707 |
| Opus 5 | $0.00031 | $0.00353 |
| Sonnet 5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
init-rules 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Claude Rules
IMPORTANT: You MUST read rule files from this skill's bundled files. Do NOT generate rules from your own knowledge.
Rule files are bundled in this skill's directory. Use ${CLAUDE_SKILL_DIR} to reference them.
Workflow
Step 1: Detect Tech Stack
Scan the current working directory to identify languages and frameworks:
| Signal | Rule File |
|---|---|
tsconfig.json or *.ts files |
languages/typescript.md |
package.json with "vue" dependency |
frameworks/vue.md |
package.json with "react" dependency |
frameworks/react.md |
src-tauri/ directory |
frameworks/tauri.md |
*.js files without tsconfig.json |
languages/javascript.md |
*.java files or pom.xml |
languages/java.md |
build.gradle.kts or *.kt files |
languages/kotlin.md |
pom.xml/build.gradle with spring-boot |
frameworks/springboot.md |
Package.swift or *.swift files |
languages/swift.md |
Swift files with import SwiftUI |
frameworks/swiftui.md |
pyproject.toml or requirements.txt |
languages/python.md |
*.html files |
languages/html.md |
*.css/*.scss files |
languages/css.md |
go.mod or *.go files |
languages/go.md |
Cargo.toml or *.rs files |
languages/rust.md |
Present detection results and ask user to confirm or adjust before proceeding.
Step 2: Read Rule Files
Read files from this skill's bundled directory using the Read tool.
Always read:
${CLAUDE_SKILL_DIR}/base/core.md${CLAUDE_SKILL_DIR}/base/git.md
Then read each detected language and framework file, e.g.:
${CLAUDE_SKILL_DIR}/languages/typescript.md${CLAUDE_SKILL_DIR}/frameworks/vue.md
Step 3: Assemble & Write CLAUDE.md
Concatenate ALL fetched content in this exact order:
<!-- Generated by init-claude-rules | https://github.com/lifedever/claude-rules -->- Empty line
- Content of
base/core.md - Content of
base/git.md - Each detected language file
- Each detected framework file
What ships with it
17 files 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.
- base/core.md 3.4 KB
- base/git.md 886 B
- frameworks/react.md 3.1 KB
- frameworks/springboot.md 3.0 KB
- frameworks/swiftui.md 3.7 KB
- frameworks/tauri.md 1.9 KB
- frameworks/vue.md 3.7 KB
- languages/css.md 2.8 KB
- languages/go.md 6.5 KB
- languages/html.md 1.9 KB
- languages/java.md 3.7 KB
- languages/javascript.md 2.1 KB
- languages/kotlin.md 3.4 KB
- languages/python.md 2.1 KB
- languages/rust.md 7.8 KB
- languages/swift.md 3.0 KB
- languages/typescript.md 2.6 KB
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.
- 2d ago First seen · 73 lines · 62 tokens per session scan A 864781fe0c6a
init-rules is a skill published in the GitHub repository lifedever/claude-rules (189 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 707 once invoked, about $0.0003 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.
Other skills, from other repositories
gemini-agents-api
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
chat_with_agent
Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, inspect what the agent actually…
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
skill-prompt-convert
在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。.