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/itismixian/orrery/agents-mdgit clone --depth 1 https://github.com/ItIsMixian/OrreryWrote 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/itismixian/orrery/agents-md)<a href="https://agentmods.dev/instructions/itismixian/orrery/agents-md"><img src="https://agentmods.dev/badge/instructions/itismixian/orrery/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 | $0.03456 | $0.03456 |
| Opus 5 | $0.01728 | $0.01728 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
Orrery 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 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orrery：Agent 状态索引
这是新会话或上下文重置后的强制入口。Orrery 正在用自身权威模型管理发布 Skill、文档观测台和上下文路由研究。
接触文件前必须阅读
AGENTS.mddocs/HANDOFF.mddocs/PROGRESS.mddocs/core/principles.md- 与任务相关的
docs/state/*.md - State 链接的有效 ADR（只在需要理解理由时）
- PROGRESS 指向的活动 Implementation Plan
- 最后读取真实代码、配置、资产、实验报告或外部运行状态
权威规则
- State Docs 只写当前事实；ADR 保存决定与原因；Plan 只写准备怎样做。
accepted不等于implemented；工作树实现不等于已提交，已提交不等于已发布。docs/library/、docs/backlog.md和experiments/没有决策权。实验通过质量门并经用户接受后才可形成 ADR。- 每次完成实现或验证，同步 State、Validation、DEVLOG；由唯一整合者按当前线路同步 PROGRESS，停止点或风险变化时同步 HANDOFF。当前入口只保留当前控制信息，历史通过链接进入 DEVLOG／Validation。
docs/_site/index.html是生成物，禁止手工编辑。
硬边界
- 默认安装不能覆盖现有作者文档；
--upgrade-tools只能操作白名单工具并先备份。 - API Key、
ai-config.json、keyring、缓存、.port、生成站点和本机原始 benchmark 不能进入发布包。 - 仪表盘、AI 问答、摘要、RAG 和趋势雷达只能投影权威文档，不能产生项目事实。
- Git 只证明写入；Agent 回执只属于自述。没有 Harness／工具边界证据时，不得宣称已精确审计模型读取内容。
- 大型原始实验根
D:\coding warehouse\project-orrery-benchmark不自动进入 Git；可发布结论必须提炼到experiments/context-routing/results/。 - 修改发布契约、文档架构或跨模块安全边界时必须新增 ADR，不得只改 README。
- 创建 Workstream 任务或追加实质范围前，唯一协调者必须先提交对应 ADR／Approved Design／Plan（含 dated scope amendment）与 Pending Validation；任务消息只传 exact authority SHA、路径、执行配置与安全边界。Agent 在首次或恢复产品写入前必须读取并登记该 scope revision；Prompt／transcript 不得成为需求、批准或验证事实。
- 并发 Workstream 必须各自使用独立分支和 linked worktree／clone；主 worktree 只用于集成。不得让两个 Agent 共享同一工作目录或把 Candidate／Worktree State 表述为 canonical。
- 普通功能分支不持续改写根
docs/PROGRESS.md与docs/HANDOFF.md；受影响的 subsystem State、实现和验证在分支同行，由唯一整合者在干净 integration worktree 中同步全局入口。 - 推广到
main前，必须先把 exact Candidate SHA 推到非 main 分支，并取得 GitHubsmoke-test (windows-latest)与smoke-test (ubuntu-latest)双 PASS；main 保护规则必须拒绝未经这两个检查的 SHA。该规则不强制 PR，但禁止先推 main 再等待验证。 - 协作功能默认必须保持 zero-network Personal Mode；Team Mode 只能由用户按项目显式开启。中央视图只读且只能发送请求，任何执行必须由成员本机确认。
- Team Mode 不得同步完整 Prompt／回答／transcript、源码正文、未 push diff 或成员执行凭据；Local-only telemetry 必须标注来源，证据不足的语义关系保持 Unknown。
project structure
ID: project-structure
What: 管理发布 Skill、根文档、实验控制面、自托管观测台和外部原始运行之间的边界。
Truth: 当前仓库树、.project-orrery.json、docs/PROGRESS.md。
Dig: 项目结构 State | ADR-0001 | ADR-0007 | ADR-0008。
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 · +5 lines · +1,336 tokens per session 013bf1a5375b
- 5d ago First seen · 93 lines · 2,120 tokens per session scan A 255f2cbc8716
Orrery AGENTS.md is an instructions file published in the GitHub repository ItIsMixian/Orrery (45 stars, last pushed 2d ago), licensed MIT. It adds 3,456 tokens to every session, about $0.0173 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
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.
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 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.