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/konghayao/peri/claude-mdgit clone --depth 1 https://github.com/KonghaYao/periWrote 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/konghayao/peri/claude-md)<a href="https://agentmods.dev/instructions/konghayao/peri/claude-md"><img src="https://agentmods.dev/badge/instructions/konghayao/peri/claude-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 | $0.01191 | $0.01191 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
peri CLAUDE.md 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 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.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Perihelion
终端 AI 编程助手, 人文交流、撰写文档以研究员风格为主，务实谨慎，不可过度营销；主路径 peri-tui → peri-acp → peri-agent::run_react_loop。执行阶段与退出语义见 peri-agent/CLAUDE.md。
先读什么
信息优先级：代码/契约测试 > docs/standards/ > 模块 CLAUDE.md > docs/design/ > active spec > history；冲突服从更高项。AgentsMdMiddleware loader 不自动继承父目录：进入模块任务前，显式 Read 对应模块 CLAUDE.md 和适用 standard。
- 标准入口：
docs/standards/index.md；架构契约：docs/standards/architecture-contracts.md；权威设计索引：docs/design/README.md。 - Rust：
docs/standards/rust.md；TUI：docs/standards/tui.md；文档维护：docs/standards/documentation.md。 - Git 分支、upstream 与 push 安全：
docs/standards/git.md。 - 测试：
docs/standards/testing.md；活动需求读对应spec/issues/；历史仅查spec/global/problems.md。
跨仓库契约
修改 ACP 边界、frozen prompt、事件链、工具可见性或序列化、中间件顺序、安全配置前，先读 docs/standards/architecture-contracts.md；根文件不复制规则正文。
任务路由
| 任务 | 先读 | 稳定入口 |
|---|---|---|
| Agent loop、Compact、provider、session runtime | peri-agent/CLAUDE.md + architecture/rust |
peri-agent/src/agent/、peri-agent/src/session/、run_react_loop |
| ACP host、stdio、prompt、event、caps | peri-acp/CLAUDE.md + architecture/rust |
peri-acp/src/host/、peri-acp/src/event/、peri-acp/src/session/ |
| Controller/Runtime、cancel、事件 envelope、Langfuse | architecture/rust + 对应 code-index | peri-controller/src/、peri-runtime/src/、peri-controller/src/langfuse/ |
| MCP、plugin、skills、subagent、HITL、tool search、LSP | peri-middlewares/CLAUDE.md + architecture/rust |
peri-middlewares/src/ |
| Workflow 注册与运行 | middleware guide + docs/code-index/peri-workflow.md |
peri-middlewares/src/workflow/、peri-workflow/src/{runner,rpc}.rs、peri-acp-types/src/workflow.rs |
| TUI | peri-tui/CLAUDE.md + tui/rust |
peri-tui/src/kit/、peri-tui/src/kit/acp_events/ |
| E2E | e2e/CLAUDE.md + testing standards |
e2e/ |
| 文档站 | peri-cool/CLAUDE.md + documentation |
peri-cool/（submodule） |
| Rust 通用、测试、CLAUDE 维护 | 对应 standard | docs/standards/、docs/standards/testing.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.
- yesterday Changed · +12 tokens per session e0a7719ace82
- 5d ago First seen · 62 lines · 1,179 tokens per session scan A 4d13022357f3
peri CLAUDE.md is an instructions file published in the GitHub repository KonghaYao/peri (160 stars, last pushed today), licensed Apache-2.0. It adds 1,191 tokens to every session, about $0.0060 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 instructions, from other repositories
openinterpreter AGENTS.md
Instructions for openinterpreter/openinterpreter, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
agentloom AGENTS.md
AGENTS.md instructions for MyAgentHubs/agentloom, covering agents.md, before you write any code, scope rules, checks you must run and pass and first stage the sidecar required by the tauri build script.
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
devo AGENTS.md
AGENTS.md instructions for 7df-lab/devo, covering agents.md, rust, tests, test assertions and protocol and session settings.
carboncode AGENTS.md
Instructions for Yapie0/carboncode, covering agents.md, project context, current status, product direction and chosen base.
chatgpt-vue3-light-mvp AGENTS.md
Instructions for pdsuwwz/chatgpt-vue3-light-mvp, a project described as: 💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持 SSE 打字机效果流式输出, 集成 markdown-it Mermaid/KaTex/LaTex 公式高亮预览, 星火, 智谱, 硅基流动, Deepseek…