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 instructions/fish827-08/rag-kb/agents-mdgit clone --depth 1 https://github.com/fish827-08/rag-kbWrote 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/fish827-08/rag-kb/agents-md)<a href="https://agentmods.dev/instructions/fish827-08/rag-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/fish827-08/rag-kb/agents-md.svg" alt="Measured on agentmods" 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 | $0.04013 | $0.04013 |
| Opus 5 | $0.02006 | $0.02006 |
| Sonnet 5 | $0.00803 | $0.00803 |
| Haiku 4.5 | $0.00401 | $0.00401 |
Grade A, and why
rag-kb AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- CUDA 版 PyTorch：本机 Python 3.10 对应 **torch 2.11.0+cu128**（已装好并验证，2026-08-23；cu124 轮子在新版已停发，勿照搬旧教程）。官方源 `download.pytorch.org` 国内仅 ~0.6MB/s，**下载走阿里云镜像** `https://mirrors.aliyun.com/pytorch-wheels/cu128/`（实测 ~6.5MB/s，curl How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — kb 项目 AI 开发指南
本文件是所有 AI 编码助手（Trae / Claude Code / Cursor 等）在本仓库工作的第一入口。先读本文件，再读设计文档，然后才开始干活。
0. 强制规则
- 开始任何编码工作前，先阅读与本次改动相关的设计文档：改动涉及哪个模块/功能，就通读对应的 spec 与计划（完整文档清单见第 1 节）。核心基线
docs/superpowers/specs/2026-08-23-kb-memory-service-design.md定义需求、架构与 API 的方式适用于全项目，是新人入门必读。 - 实现与设计文档冲突时：停下来向用户确认，先修订文档再改代码。
- 仓库内除设计文档与本文件外的所有文档均已作废（见第 1 节），禁止从中提取需求、架构或约定。
验证协议（2026-08-31 定稿）
| 变更级别 | 设计文档范围 | 测试范围 |
|---|---|---|
| 小改动 / 功能迭代（常规） | 只读相关 spec | 只跑相关测试（改动涉及的模块/功能的验收测试 + 单元测试） |
| 版本大更新 / 核心架构改变 | 通读相应 spec 链 | 全量测试（kb 套件 pytest tests/） |
| orchestra（B 线） | — | 冻结不测：任何情况下不跑 orchestra/tests/，也不为其改动做验证开销 |
其余红线不变：先测后实现（TDD）；任何 AI 不得代替人工声称"验收已完成"；交付时出具"自动化已覆盖 / 待人工验证"两部分。
1. 文档有效性声明
| 路径 | 状态 | 说明 |
|---|---|---|
docs/superpowers/specs/2026-08-23-kb-memory-service-design.md |
✅ 唯一有效设计 | 需求、架构、API、里程碑全在这里（已实施完成，2026-08-24 收口） |
AGENTS.md（本文件） |
✅ 有效 | AI 工作规则 |
ROADMAP.md |
✅ 有效 | 项目发展总线设计书（人类入口：树形路线+进度；2026-08-24 v2 总线定稿） |
PROJECT.md |
✅ 有效 | 接力文档（项目状态/进度看板/接手指南；新 AI 必读第 2 份，2026-08-24 新增） |
docs/USER_GUIDE.md |
✅ 有效 | 用户使用手册（人类用户入口：kb 使用 + MCP 挂载 + orchestra 协作流程，2026-08-24 新增） |
docs/superpowers/plans/2026-08-23-kb-dev-nodes.md |
✅ 有效 | 节点计划（门禁与验收测试，N1-N16 全部完成） |
docs/superpowers/specs/2026-08-24-logging-design.md |
✅ 有效 | 日志设计（总线 A1.2，N17-N18 实施依据） |
docs/superpowers/plans/2026-08-24-p2-roadmap.md |
✅ 有效 | kb 功能路线（总线 A2-A4：鉴权→遗忘→CLI/Web UI） |
orchestra/protocol.md + worker-prompt.md + coordinator-prompt.md |
✅ 有效 | orchestra 协作协议三件套（v1.1：任务分支/重启管控/交流窗） |
orchestra/docs/superpowers/plans/2026-08-24-orchestra-v2-iteration.md |
✅ 有效 | orchestra v2 迭代计划（总线 B1 P0 载体；V2-0 修复卡保留，其余节点按总线 B1.1-B1.7 编号演进） |
README.md |
✅ 有效 | 项目说明（N16 按新定位重写：快速开始 / MCP 挂载 / 端点速查） |
docs/AGENT_PROMPT.md / AGENT_PROMPT_EN.md |
✅ 有效 | 通用 Agent 接入提示词（客户端无关；另封装为 skills/kb-memory/SKILL.md，安装见 scripts/README.md） |
docs/superpowers/specs/2026-08-30-memory-scope-refactor-design.md |
✅ 有效（隔离语义已取代） | 记忆范围重构 v2（2026-08-30 收口）：隔离键改 client+project（agent_id 降为主键冗余）、MCP 工具去 agent_id、审计文件 client__project、遗忘时钟注入验证；其 (client, project) 隔离语义已被 v3 取代（见下行） |
docs/superpowers/specs/2026-08-31-memory-share-refactor-design.md |
✅ 有效 | 记忆全共享 v3（2026-08-31 定稿）：去除 (client, project) 隔离——所有记忆/知识全共享，client/project 降级为审计归类与元数据；取代 v2 的隔离语义 |
.mcp.json |
✅ 有效 | 项目级 MCP 挂载配置（Claude Code 等在本目录启动即连 kb 服务） |
_archive/（含旧 README.md、旧 ROADMAP.md、step_doc/、notes/、rag_kb/、app/、demo.py、test_py/、data/） |
❌ 已归档（2026-08-23/24） | 旧学习项目全部内容；禁止参考其架构与实现，不在其上续写（注意：归档内旧 ROADMAP.md 与根目录新 ROADMAP.md 无关） |
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 Changed · +11 lines · +381 tokens per session d3bcb6a1c12d
- 5d ago First seen · 100 lines · 3,632 tokens per session scan A 6d751eae5757
rag-kb AGENTS.md is an instructions file published in the GitHub repository fish827-08/rag-kb (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,013 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).