agentmods.dev

peri: Instructions file for Claude Code

CLAUDE.md

peri CLAUDE.md is an instructions file for Claude Code from KonghaYao/peri. It costs 1,681 tokens per session, scanned A, original, Apache-2.0.

A development guide for Perihelion, a terminal-based AI programming assistant written across several Rust modules. It explains which documentation and module instructions to read before changing different parts of the system.

In plain words
What is it for?
Use it to route work involving the agent loop, sessions, ACP communication, terminal interface, events, tools, configuration, tests, documentation, or Git operations.
Why use it?
It helps agents follow the project’s priority rules and preserve contracts between repositories and modules. This lowers the risk of breaking prompts, events, serialization, security settings, or workflow behavior.

Instructions file for Claude Code

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

This is KonghaYao/peri's own configuration. It tells Claude Code how to work on peri 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 peri configures →

not rated 247repo +3 changed 11d ago A scan 1,681 tokens original Apache-2.0
View source ↗ KonghaYao/peri docs.peri-code.dev
Reuse

Borrowing it

Nothing to install: this file belongs to KonghaYao/peri. 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/KonghaYao/peri/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KonghaYao/peri

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 peri CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/konghayao/peri/claude-md/github.svg)](https://agentmods.dev/instructions/konghayao/peri/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/konghayao/peri/claude-md"><img src="https://agentmods.dev/badge/instructions/konghayao/peri/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 peri CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/konghayao/peri/claude-md"><img src="https://agentmods.dev/badge/instructions/konghayao/peri/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,681 This file is loaded in full into every session.
When invoked 1,681 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01681 $0.01681
Opus 5.5 $0.00672 $0.00672
Sonnet 5.5 $0.00336 $0.00336
Haiku 4.5 $0.00168 $0.00168

Measured 11d ago against content hash e7a6a060cc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 11d 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.

CLAUDE.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Peri 是终端 AI 编程助手：用户交付任务，Agent 推进工作，过程可理解、可介入，结果可核对。长期可维护性是设计目标。

项目大目标

v4 分阶段推进存算分离。阶段状态以代码、契约测试及 active spec 为准。

  • 单机本地：已完成。 本地 Agent、会话与工具形成可用闭环。
  • 单机服务化：未完成。 TS SDK 负责服务入口、进程与跨主 Agent 管理；Peri 负责 ACP 后端、Agent 执行、Store 直连和 MCP Client。进程重启后保留历史会话加载与正常续聊，不恢复旧 Agent 执行。
  • 集群化 / Serverless 化：未完成。 推进多实例协调与接管、工具环境独立驻留及云端部署；计算核心减少重型依赖，支持实例替换，Agent 决策、模型推理和工具执行可分开部署。
  1. Harness：RCRA（Receive → Compact → Reason → Act）循环执行，hook 扩展生命周期，Middleware 承载业务能力。
  2. Sessions：存储会话、消息、配置及冻结上下文，不持久化 Agent 执行恢复状态；后端可替换；会话、任务运行与计算实例具有独立生命周期。
  3. Resources：文件系统工具、Skill、Cron 等能力经 MCP Middleware 接入；工作区与工具环境可独立于计算实例驻留。
  4. Orchestration：基于同构 Agent，管理 Subagent、Multitask 与 Workflow 的任务关系、协调与当前运行期等待；不恢复旧执行。Middleware 提供接入，编排生命周期不绑定某个活跃 Harness 实例。
  5. Endpoint：ACP 是统一出口协议，stdio 是本地传输方式；传输层可自定义，客户端复用同一业务语义。

内部依赖走 MCP，外部出口走 ACP：依赖按能力消费方向定义，与部署位置无关；MCP 能力边界不强制对应独立进程，部署隔离按信任边界和生命周期确定。 减少文件系统依赖，推崇网络依赖：文件系统依赖转移到 mcp-packages 层以下，不可外溢。

核心工程原则 v1.5

  1. 架构与领域优先：编码前明确目标、领域边界、职责、依赖方向和数据流。复用型抽象等第二个真实用例再提取；协议隔离、依赖反转和确定的可替换边界可在首个用例建立接口，须说明当前需要。
  2. 模块封装复杂度：接口精简、稳定，文件按职责拆分；规模限制及验证遵循 STD-SIZE-001。
  3. 显式表达领域语义。 命名与类型表达职责、身份、状态和错误；所有权和副作用可见，避免字符串约定与隐式共享。
  4. 边界与数据流清晰：协议、领域、持久化与视图模型各守边界；在边界校验和转换，避免跨层共享可变状态。
  5. 保留维护上下文：记录决策原因、影响与风险，临时方案注明移除条件；技术债务关联任务，关键决策同步文档，不留无上下文的 TODO。
  6. 删除优于兼容：内部重构删除过时实现，不新增兼容层、deprecated shim 或双写；对外兼容义务按协议评估。
  7. 业务规则单一权威：同一领域规则只维护一份实现；允许多个存储后端和协议 adapter 封装适配差异，共用业务规则与契约。
  8. 优先验证完整行为：先验证用户可观察的行为，再按风险补齐回归、失败和生命周期测试；遵循 testing.md。
  9. 在授权范围内主动闭环。 依据仓库证据处理常规选择；澄清目标、权限或不可逆结果的歧义。异议须说明代价和替代方案。
  10. 修复一类问题，而不是一个问题
  11. 暴露异常优于简单掩盖：如果没有任何说明，默认的错误处理方式都是抛出，并在日志中留下记录。
  12. 数据库表结构须经用户明确批准：变更前说明表及结构的合理性，由用户裁决。

行事风格

  • 像研究员一样判断，像工程师一样交付。 区分观察、推断和假设，以代码、复现或实验支持结论；说明局限，不补造数字，不把命令启动当成完成。
  • 汇报风格：用户有阅读障碍，减少字数，多用 order list 结构化表达。

事实源与任务路由

先读 标准索引，区分现状与目标。按 docs/code-index/ 核实入口、同步变更。Peri loader 不继承父目录，须显式读取模块指引。

任务 先读
Agent loop、Compact、provider、session peri-agent/CLAUDE.md + architecture/rust
ACP host、stdio、prompt、event、caps peri-acp/CLAUDE.md + architecture/rust
Controller/Runtime、cancel、Langfuse architecture/rust + 对应 code-index
MCP（含内置实例）、plugin、skills、subagent、HITL、工具 middlewares 与 mcp-packages/CLAUDE.md + architecture/rust
Workflow middleware guide + docs/code-index/peri-workflow.md
TUI peri-tui/CLAUDE.md + tui/rust；集成用例 docs/verification/tui-integration-cases/
E2E e2e/CLAUDE.md + testing
交付验证 scripts/check-changed.sh、scripts/verify-async.sh（开工先读 read）
文档站 peri-cool/CLAUDE.md + documentation
历史学习 .claude/skills/learn-from-history/SKILL.md

Read the full file on GitHub · 74 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. 11d ago Changed · +1 lines · +14 tokens per session e7a6a060cc7f
  2. 17d ago Changed · -4 lines · -12 tokens per session f395a585db1a
  3. 1mo ago Changed · +6 lines · +4 tokens per session 463d28ae357b
  4. 1mo ago Changed · +9 lines · +487 tokens per session af724281c3a2
  5. 1mo ago Changed · -3 tokens per session 038640354ff8
  6. 1mo ago Changed · +12 tokens per session e0a7719ace82
  7. 1mo ago First seen · 62 lines · 1,179 tokens per session scan A 4d13022357f3

Subscribe to this mod's changes

peri CLAUDE.md is an instructions file published in the GitHub repository KonghaYao/peri (247 stars, last pushed today), licensed Apache-2.0. It adds 1,681 tokens to every session, about $0.0067 per session on Opus 5.5. 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.

Claude CodeGLMacpcoding-agentdeepseekmcp
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 · 7,461 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

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens