odai AGENTS.md

odai AGENTS.md is an instructions file for Codex, OpenCode from orziz/odai. It costs 1,852 tokens per session, scanned A, original, MIT.

Repository instructions that define how to maintain the odai project, including which files are the official source for its skills and how releases are handled.

In plain words
What is it for?
Use them when changing odai, its skills, packaging, release process, or integration with dsh.
Why use it?
They prevent contributors from editing generated copies or bypassing the project's required checks and boundaries.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/orziz/odai/agents-md
Clone the repo
git clone --depth 1 https://github.com/orziz/odai

Made for: Codex, OpenCode.

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 odai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/orziz/odai/agents-md.svg)](https://agentmods.dev/instructions/orziz/odai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/orziz/odai/agents-md"><img src="https://agentmods.dev/badge/instructions/orziz/odai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,852 This file is loaded in full into every session.
When invoked 1,852 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01852 $0.01852
Opus 5 $0.00926 $0.00926
Sonnet 5 $0.00370 $0.00370
Haiku 4.5 $0.00185 $0.00185

Measured yesterday against content hash 394562efd580, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

odai 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

仓库维护约束

odai 必用

  • 本仓库中的每次用户请求都必须使用 canonical skills/odai/SKILL.md 治理。若宿主明确声明当前 odai-dsh-agentodai-dsh-plugin 已把完整 canonical governance 注入系统提示,并给出 skill version、runtime contract 与 bundle digest,则该注入本身视为已完整加载;声明有效且本会话未改动 canonical bundle 期间,不得再调用 skill 或 read 重复载入同一正文。仅当注入声明缺失或不可信、任务直接审查或修改 Odai、或 manifest 声明的 canonical 文件在注入后发生变化时,才须在行动前完整读取当前 SKILL.md,并以新内容继续治理。其他宿主若当前任务尚未完整读取其当下版本,任何调查、判断、修改或测试前先完整读取。
  • 按 odai 的真实缺口决定是否读取支撑资料;使用 odai 不等于自动增加计划、路由、角色、文件、测试或流程,简单任务仍直接完成。
  • 对 odai 自身及其配套机制的修改同样受 odai 治理:先判断是否必要、是否比现状更成事、是否有可验证净增益,再决定保留、修改或退役,不因已有实现、历史方案、题本得分或局部可实现性继续堆叠。
  • 以减少 token、延迟或成本为目的的优化,必须先用行为契约、反例与测试证明既有能力和安全边界不退化,再评估节省是否成立;不能验证保持项、只测预算下降、依赖模型自报或以删除能力换取指标时,不得合入或发布。
  • 评测维护、题本设计、裁判与报告整理仍按上述要求治理;真正受测的 runner 则严格服从冻结的评测臂,不继承本节。on 只加载该臂声明的冻结 skill 与项目材料;off 必须在干净隔离环境运行,不读取或注入 odai、.odai/local.md、odai 路由或 Hooks、要求使用 odai 的仓库指令、其他臂输出、既往 runner 转录或其派生状态。

官方 skills 单一事实源

  • skills/odai/skills/ribao/ 是各自唯一可编辑的 canonical source;odai 是统一入口与最终交付 owner,ribao 是可独立加载的专业汇报能力。
  • cli/skills/ 不在仓库中常驻;它只由 npm prepack 临时生成,并在 postpack 清理。
  • 即使用户或 IDE 指向打包期间临时出现的 cli/skills/,也要把对应修改落到仓库根 skills/<name>/
  • source 修改完成后,运行 node scripts/validate-odai-skill.mjs 验证 canonical skills。
  • canonical references 按单一所有权维护:references/planning.md 只负责正式计划、可执行合同与跨轮续作,references/craft.md 只负责已决定结果的制作工艺,references/leverage.md 只负责能力与责任选择、调度和交接;角色合同只引用对应 owner,不复制另一层的清单或宿主机制。
  • odai-cli 未冻结时,发布相关修改还需运行 npm --prefix cli run pack:dry-run,确认产物与当前声明的打包范围一致,且命令结束后没有遗留 cli/skills/;冻结期间遵循下节边界。

odai-cli 冻结边界

  • cli/plans/odai-cli-plan.mdplans/odai-cli-runtime-canary.md 当前冻结,不属于 active canonical / DSH 维护与验收范围。除非用户明确重新开放,不修改、测试、打包、升版或发布 odai-cli,也不为兼容它改变 canonical 或 DSH 路线。
  • 冻结期间,canonical / DSH 变更不运行 CLI tests 或 npm --prefix cli run pack:dry-run;只记录可能影响未来恢复的已知差异。cli/skills/ 仍不得作为可编辑 source 或遗留在仓库中。

版本发布约束

  • 从本约束生效后的首个候选版本起,本仓库自有的任何新版本标识都不得包含数字字符 4;npm package version、skill version 与 runtime contract version 均受约束,版本序列遇到含 4 的候选值时必须直接跳过。已发布历史版本及其兼容记录必须按事实保留,不因本约束改写;上游依赖版本不属于本仓库自有版本,不受此规则限制。
  • 禁止只靠人工记忆执行本约束。所有发布入口与版本事实源必须调用仓库的统一版本策略校验;新增版本载体时必须同时纳入该校验,命中禁用字符即 fail-closed。
  • 同一 npm 候选从未发生过 registry publish,且未废弃或经用户明确拆分时,后续改动继续归入该候选;不得仅因新一轮任务、canonical / runtime contract 变化或新增 changelog 内容另起包版本,也不得把当前候选写成历史。版本一旦曾发布,即使后来 unpublish 或 deprecate,该标识也视为已消耗,不得复用。改版本前先核对 package metadata、当前唯一 Unreleased owner 与真实 registry 发布事实。

Read the full file on GitHub · 40 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. yesterday Changed · +6 lines · +286 tokens per session 394562efd580
  2. 5d ago First seen · 34 lines · 1,566 tokens per session scan A 53a3a9bf40a4

Subscribe to this mod's changes

odai AGENTS.md is an instructions file published in the GitHub repository orziz/odai (107 stars, last pushed yesterday), licensed MIT. It adds 1,852 tokens to every session, about $0.0093 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.

Related

Other instructions, from other repositories

dsh-enhanced-plugins AGENTS.md

Instructions for sky-unicorn/dsh-enhanced-plugins, covering agents.md — deepseek harness 插件项目通用规则, 权威来源与开始工作前的检查, 插件架构与职责边界, cordis 插件与生命周期 and 配置与 settings.

sky-unicorn/dsh-enhanced-plugins · 3,872 tokens

dsh-virtual-product-team AGENTS.md

AGENTS.md instructions for songoao25/dsh-virtual-product-team, covering agents.md — 给 ai 编码助手/agent 的仓库说明, 这是什么, 仓库结构, 关键约定 and 常用命令.

songoao25/dsh-virtual-product-team · 603 tokens

deepseek-harness CLAUDE.md

Claude Code instructions for deepseek-ai/deepseek-harness, a project described as: DeepSeek Harness: Everything is a Plugin.

deepseek-ai/deepseek-harness · 3 tokens

dsh-config-manager AGENTS.md

Instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🗣️ 语言与交流, 📦 项目概览, 🗂️ 仓库结构与职责 and ui 分层(改动前必读,避免放错层).

xiajiajun516/dsh-config-manager · 7,380 tokens

dsh-industry-research AGENTS.md

AGENTS.md instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.

PerryLink/dsh-industry-research · 1,386 tokens

dsh-checkpoint-rewind AGENTS.md

AGENTS.md instructions for PerryLink/dsh-checkpoint-rewind, covering agents.md, 仓库布局:发布面 / 本地工程面, 命令, 提交纪律 and dsh 插件约束(红线).

PerryLink/dsh-checkpoint-rewind · 2,211 tokens