Borrowing it
Nothing to install: this file belongs to xhwSkhizein/agiwo. 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/xhwSkhizein/agiwo/main/AGENTS.mdgit clone --depth 1 https://github.com/xhwSkhizein/agiwoWrote 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/xhwskhizein/agiwo/agents-md)<a href="https://agentmods.dev/instructions/xhwskhizein/agiwo/agents-md"><img src="https://agentmods.dev/badge/instructions/xhwskhizein/agiwo/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 | $0.06762 | $0.06762 |
| Opus 5 | $0.03381 | $0.03381 |
| Sonnet 5 | $0.01352 | $0.01352 |
| Haiku 4.5 | $0.00676 | $0.00676 |
Grade A, and why
agiwo AGENTS.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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agiwo 开发指南。供 AI 编码助手和开发者快速理解当前仓库结构、边界和约定。
本文件只维护“目录级职责 + 稳定 API/边界”，不再逐个文件镜像源码；实现细节以源码为准。
How To Use This File
- 如果文档与源码冲突，以源码为准，并顺手更新本文件。
- 优先用本文件定位“应该去哪个目录/模块看”，不要把它当成逐文件索引。
- 如果某条信息很难长期与源码同步，就应该提升抽象层级或直接删掉。
Truth Source Order (ADR 0048 / 0049)
CONTEXT.md— 现行领域语言（Session / MainAgent / Run / RunLog / SessionIntent / Worker / 瘦 Scheduler）docs/adr/README.md现行阅读顺序中的 ADR（以 0048、0049 为首）- 源码
已被 0048 取代的 ADR 已移出 docs/adr/（见 trash/adr-superseded-by-0048-* 与 git 历史）；trash/、历史施工计划不是规格。作废词（Objective、Assignment、Turn 聚合、RootRunRequested 等）不得再指导实现或出现在新的公开 API / 领域测试断言中。0049 是目标分层（MainAgent / SessionIntent / 瘦 Scheduler），补充而非取代 0048。切换破坏性：清理开发库，无 migration。
Logging
统一日志格式：logger.{level}("event_name", key=value, ...). 详见 docs/logging-guidelines.md.
Config Hot Reload
配置热更仅在 agent 为 IDLE/COMPLETED/FAILED 状态时生效，运行中 agent 配置延迟生效。详见 docs/config-hot-reload.md.
Repository Layout
SDK (agiwo/)
| Path | Responsibility |
|---|---|
agiwo/agent/ |
Canonical agent runtime。public API 只从 agiwo.agent 暴露；顶层保留稳定入口与核心 orchestrator（agent.py、execution_handle.py、run_resume.py、run_loop.py 及 run_loop_* 阶段模块、definition.py、llm_caller.py、tool_executor.py、prompt.py、trace_writer.py）。纯数据模型收口在 models/，hook contract 收口在 agiwo.agent.hooks，nested-agent adapter 收口在 nested/（含 child_ops），run/session runtime context、state helper 与 RunStateWriter 严格写路径收口在 agiwo.agent.runtime，termination logic 收口在 termination/，可恢复中断收口在 pause.py / resume.py，结构化重试收口在 retry/，plan/ 拥有 RunPlan 规范化与 update_plan 系统工具，轨迹自省与 context repair 收口在 introspect/，storage/ 负责持久化。main_agent.py / spec.py / queue.py 拥有 Session 级 MainAgent；worker_port.py / worker.py 定义 Worker 协议与 MainAgent 侧服务（Scheduler 实现见 agiwo.scheduler.worker_bridge）。run_loop.py 是唯一的单次 run execution owner；agiwo.agent.runtime 只承载 context / session / writer，不得再暴露 execution-owner alias。 |
agiwo/llm/ |
Model 抽象、Provider 适配器、配置策略、消息/事件归一化，以及统一的 model factory。 |
agiwo/tool/ |
Tool 抽象、最小执行上下文、builtin tools、后台进程 registry（process/），以及工具侧存储（如 citation）。 |
agiwo/scheduler/ |
Agent 之上的编排层：child 委派树与 waitset。engine.py 定义公开 Scheduler facade（lifecycle + waitset/cancel/查询 API），_tick.py 是编排 tick owner，runner.py 负责单次 dispatch；completion 在 runner_completion.py，commands.py 承载调度动作与 tool DTO，runtime_state.py 承载进程内 live state，tool_control.py / runtime_tools.py 收口 spawn/sleep/cancel，store/ 只负责 AgentState 持久化。Session 产品入口是 MainAgent.accept，不是 Scheduler root dispatch（ADR 0049）。 |
agiwo/observability/ |
Trace/Span 模型、查询接口与 trace storage 实现；agent runtime 的 Trace 投影层收口在 agiwo/agent/trace_writer.py，并以 committed RunLog facts 为输入构建 Trace view。 |
agiwo/embedding/ |
Embedding 抽象与 factory，包含本地/OpenAI 风格实现。 |
agiwo/skill/ |
Skill 的发现、路径规则（config.py）、加载、注册、异常定义，以及 SkillTool 桥接。 |
agiwo/workspace/ |
Agent workspace 路径语义、模板/bootstrap、工作区文档读取与变更 token。 |
agiwo/memory/ |
共享 MEMORY 索引/切块/搜索能力，以及 WorkspaceMemoryService；默认检索 hook（DefaultMemoryHook / filter_relevant_memories）收口在 defaults.py。 |
agiwo/config/ |
SDK 全局配置入口、Provider 枚举与共享设置。 |
agiwo/utils/ |
跨模块运行时工具。storage_support/ 负责共享 SQLite/Mongo runtime、schema/index 初始化等基础设施。 |
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.
- 8d ago First seen · 264 lines · 6,762 tokens per session scan A c821e58ccfd7
agiwo AGENTS.md is an instructions file published in the GitHub repository xhwSkhizein/agiwo (10 stars, last pushed 1mo ago), licensed MIT. It adds 6,762 tokens to every session, about $0.0338 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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).
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.
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.