agentmods.dev

spring-ai-loom-agent: Instructions file for Claude Code

CLAUDE.md

spring-ai-loom-agent CLAUDE.md is an instructions file for Claude Code from wb04307201/spring-ai-loom-agent. It costs 16,803 tokens per session, scanned C, original, Apache-2.0.

Repository guidance for Spring AI LoomAgent, a Spring Boot library that adds a chat interface, document search, tool calling, skills, and user roles to Spring AI applications. It also describes the Java, Maven, database, and migration setup.

In plain words
What is it for?
Use it when working on the chat UI, knowledge search, tool connections, skills, permissions, modules, or database migrations.
Why use it?
It gives agents the architecture and project conventions needed to change a multi-module Java application safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is wb04307201/spring-ai-loom-agent's own configuration. It tells Claude Code how to work on spring-ai-loom-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spring-ai-loom-agent configures →

not rated 327repo changed 18d ago C scan 16,803 tokens original Apache-2.0
View source ↗ wb04307201/spring-ai-loom-agent
Reuse

Borrowing it

Nothing to install: this file belongs to wb04307201/spring-ai-loom-agent. 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/wb04307201/spring-ai-loom-agent/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wb04307201/spring-ai-loom-agent

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.

agentmods badge for spring-ai-loom-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wb04307201/spring-ai-loom-agent/claude-md/github.svg)](https://agentmods.dev/instructions/wb04307201/spring-ai-loom-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wb04307201/spring-ai-loom-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/wb04307201/spring-ai-loom-agent/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.

agentmods 80×15 button for spring-ai-loom-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wb04307201/spring-ai-loom-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/wb04307201/spring-ai-loom-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16,803 This file is loaded in full into every session.
When invoked 16,803 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.16803 $0.16803
Opus 5.5 $0.06721 $0.06721
Sonnet 5.5 $0.03361 $0.03361
Haiku 4.5 $0.01680 $0.01680

Measured 18d ago against content hash 80e314ac397d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

spring-ai-loom-agent CLAUDE.md scanned grade C 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 18d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Schema** (单一 V1.0 一站式 init,**项目只跑全新库**;任何已有 V1/V2 历史部署必须 `flyway baseline` 或 `rm -rf ~/.loom/datasource` 重跑):
CLAUDE.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Spring AI LoomAgent — A Spring Boot auto-configuration library that provides an out-of-the-box chat UI with RAG knowledge base, MCP tool calling, Skill library + Skill market, and role-based access (RBAC) for Spring AI applications.

  • JDK: 25+
  • Framework: Spring Boot 4.x + Spring AI 2.x
  • Build: Maven (multi-module)
  • Database: H2 (default), with Flyway migrations
  • No CHANGELOG: this project does not maintain a CHANGELOG.md — read git log for the change history

Project Overview Images

docs/project-overview-en.png and docs/project-overview-zh.png (shown at the top of README.md / README.zh-CN.md) are generated by the project skill at .claude/skills/project-overview-image/ via a deterministic pipeline (2026-09-19 起取代 wan2.7-image 文生图 —— 旧 zh 图实测重复卡/章节跳号等随机缺陷压不住):generate.py 的 DATA(结构)+ LABELS(双语文案)是布局单一真源 → 自包含 HTML/CSS(科技风:近黑蓝墨底 + 浮起暗面板 + 霓虹青唯一强调色 + 等宽字体点缀,2026-10-04 改版)→ 本地无头 Chromium(Playwright)截图 1600×840 @2x = 3200×1680;统计胶囊与小注的 universal/RBAC 数字由 TOOLS 卡片集合推导(universal_count() / rbac_count(),分类真源是 UNIVERSAL_IDS / RBAC_IDS 两个 frozenset)—— 加工具只需动 TOOLS 与对应集合,不必再手工同步计数。check.py 静态校验结构自洽/工具分类不重叠不遗漏/LABELS 与 COPY 双语键对齐/版式文案齐全/产物尺寸。改内容 = 改 generate.py 的 DATA/LABELS/COPY;配色与版式 = 改该文件的视觉 token 与 build() 内 CSS。依赖仅 pip install playwright && playwright install chromium(不再需要 DASHSCOPE key)。Regenerate via the skill trigger phrases ("更新项目概览图", "刷新 README 顶部的 overview 图", "生成 docs/project-overview-{en,zh}.png") whenever the architecture changes meaningfully — never hand-edit the PNGs;改内容 = 改 generate.py 的 DATA/LABELS。

Module Structure

Module Purpose
spring-ai-loom-agent Core library — chat, knowledge base, file, MCP, skill (market + role auth), RBAC (user/role/mcp), user interfaces + default implementations, H2-backed JVector vector store (loom_vector_store), H2 schema, static frontend resources
spring-ai-loom-agent-spring-boot-autoconfigure LoomAgentConfiguration with 7 nested static @Configuration classes (Infrastructure, Chat, Rag, Mcp, Tool, Storage, Web) — @AutoConfiguration with @ConditionalOnMissingBean on all beans for full replaceability
spring-ai-loom-agent-spring-boot-starter Empty JAR that depends on autoconfigure — the one dependency users add
spring-ai-loom-agent-test Test application with application.yml — run locally to verify changes
loom-{file,http,process,git,maven,compile}-core 无 Spring 依赖的纯操作层（FileOperations / HttpEngine / ProcessUtils / GitOperations / MavenOperations / CompileAndDeployOperations）— 主库工具是它们的薄包装；loom-file-core 另含 PathSecurityUtils（沙箱/ symlink 校验）+ LoomPaths（全仓路径派生单一真源：userRoot（内建 username 消毒）/ userFileDir / userCompileWorkspacesDir / DEFAULT_USERS_BASE）
loom-http-core 无 Spring 依赖的纯 HTTP 引擎 + 存储服务（HttpEngine + HttpStorage + HttpConfig + ProfileService/SystemService/EndpointService/HistoryService/InvokeService 等）
loom-http-mcp 独立可运行的 MCP server（19 个 @McpTool snake_case + 4 个 @McpResource）；basePath 默认 ~/.loom/http-mcp/（不与 ~/.loom/mcp/ 共享,避免 profile 凭据混入 loom-file-mcp 可读沙箱）
loom-{file,git,maven,compile}-mcp 独立可运行的 MCP server（各自 *McpProperties + application.yml）。路径双轨制：主库（多租户）一切用户路径经 LoomPaths 从 usersBasePath 派生；MCP server（单租户进程）走扁平 basePath 参数配置，4 个 server 默认共享沙箱 ~/.loom/mcp（git clone 的仓库 file/maven MCP 可直接互操作）

Read the full file on GitHub · 341 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. 18d ago Changed · +28 lines · +3,213 tokens per session 80e314ac397d
  2. 1mo ago Changed · +416 tokens per session d2a8b56910fa
  3. 1mo ago Changed · +680 tokens per session acf4c5e47c2e
  4. 1mo ago Changed · +2 lines · +1,234 tokens per session 26bd78e2dcc0
  5. 1mo ago Changed · +45 lines · +4,410 tokens per session a1aea3156622
  6. 1mo ago Changed · +97 lines · +1,911 tokens per session cb6b88236bd2
  7. 1mo ago First seen · 169 lines · 4,939 tokens per session scan C 3def1315e317

Subscribe to this mod's changes

spring-ai-loom-agent CLAUDE.md is an instructions file published in the GitHub repository wb04307201/spring-ai-loom-agent (327 stars, last pushed 18d ago), licensed Apache-2.0. It adds 16,803 tokens to every session, about $0.0672 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agentspring-ai
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

denoland/deno · 3,077 tokens