Borrowing it
Nothing to install: this file belongs to XRenSiu/claude-code-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/XRenSiu/claude-code-forge/main/CLAUDE.mdgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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.
[](https://agentmods.dev/instructions/xrensiu/claude-code-forge/claude-md)<a href="https://agentmods.dev/instructions/xrensiu/claude-code-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/xrensiu/claude-code-forge/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.
<a href="https://agentmods.dev/instructions/xrensiu/claude-code-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/xrensiu/claude-code-forge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03069 | $0.03069 |
| Opus 5.5 | $0.01228 | $0.01228 |
| Sonnet 5.5 | $0.00614 | $0.00614 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade B, and why
claude-code-forge CLAUDE.md 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 1mo 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.
4. **本机启用**：在 `~/.claude/settings.json` 的 `enabledPlugins` 字典加一条： How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Forge - 项目规范
这是 Claude Code 插件市场项目。结构：.claude-plugin/marketplace.json → plugins/<name>/ → skills / agents / rules。
版本管理
使用语义化版本 (SemVer)。三处版本必须同步：
| 文件 | 作用 |
|---|---|
plugins/<name>/skills/<skill>/SKILL.md frontmatter version |
Skill 自身版本 |
plugins/<name>/.claude-plugin/plugin.json version |
插件版本（源头） |
.claude-plugin/marketplace.json 对应插件的 version |
市场注册表（与 plugin.json 同步） |
什么时候 bump
| 变更类型 | Skill 版本 | Plugin 版本 | 示例 |
|---|---|---|---|
| 修复 typo / 格式调整 | patch (+0.0.1) | patch (+0.0.1) | 1.0.0 → 1.0.1 |
| 功能增强 / 流程变更 | minor (+0.1.0) | minor (+0.1.0) | 1.0.0 → 1.1.0 |
| 不兼容变更 / 重大重构 | major (+1.0.0) | major (+1.0.0) | 1.0.0 → 2.0.0 |
| 新增 skill / agent | — | minor (+0.1.0) | 1.1.0 → 1.2.0 |
修改文件后的同步清单
修改 skill 内容时，必须同时更新：
- 该 skill 的
SKILL.mdfrontmatterversion plugins/<name>/.claude-plugin/plugin.json的version.claude-plugin/marketplace.json中对应插件的version
新增 skill / agent 时，更新第 2、3 项。
新建插件（plugin）的额外步骤
新增整个 plugin（不是给已存在 plugin 加 skill/agent）时，除上面三处外还要做：
- 本机启用：在
~/.claude/settings.json的enabledPlugins字典加一条："enabledPlugins": { "<plugin-name>@claude-code-forge": true } - 同步 plugin cache：session 启动从
~/.claude/plugins/cache/<marketplace>/<plugin>/<version>/读 skill 索引，不是从源仓库读。未推送到 GitHub 前/plugin install拿不到新 plugin，手动复制：
并在cp -R plugins/<name> ~/.claude/plugins/cache/claude-code-forge/<name>/<version>~/.claude/plugins/installed_plugins.json加一条"<name>@claude-code-forge"（照抄已有条目的形状，installPath指向上面的目录）。 - 重启 Claude Code 会话——
Skill工具的可用列表在 session 启动时定型，运行中改settings.json/ cache 不会热加载。
第 4-6 步是用户级、不入 git 的本机配置，但它决定了你能不能调用新 plugin 的 skill。漏了它就会得到 Unknown skill 报错，且本会话无法补救（必须新开 session）。
历史 bug：
bespoke-design-systemv1.8.0 完整注册到marketplace.json但漏了enabledPlugins，导致用户调/bespoke-design-system时 Skill 工具找不到；v1.9.0 前 4 项全对仍 Unknown skill，根因是 cache 目录缺失。详见 memoryfeedback_plugin_enable_required.md/feedback_plugin_cache_must_sync.md。
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.
- 1mo ago Changed · +5 lines · +173 tokens per session 8e293e58e9ce
- 1mo ago First seen · 177 lines · 2,896 tokens per session scan B bca42a7a3301
claude-code-forge CLAUDE.md is an instructions file published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 3,069 tokens to every session, about $0.0123 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.