comet: Instructions file for Codex

AGENTS.md

comet AGENTS.md is an instructions file for Codex, OpenCode from rpamis/comet. It costs 6,833 tokens per session, scanned A, original, MIT.

A set of project instructions for rpamis/comet, written in Chinese. It covers reply language, testing, formatting, commit messages, and project structure.

In plain words
What is it for?
Use it to guide Chinese-language responses, choose tests based on change risk, run formatting and lint checks, and follow commit conventions.
Why use it?
It gives contributors shared rules for checking and submitting code, reducing inconsistent project practices.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is rpamis/comet's own configuration. It tells Codex and OpenCode how to work on comet 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 comet configures →

About the project

Comet is a resumable workflow and skill platform for coding tasks, covering requirements work as well as skill creation, evaluation, and release. It supports separate Native and Classic workflows and can coordinate implementation and verification across isolated Git worktrees. The catalogue contains skills and instructions that implement Comet-related workflows.

rpamis/comet · 3,274 stars · on GitHub · docs.comet.rpamis.com

Reuse

Borrowing it

Nothing to install: this file belongs to rpamis/comet. 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/rpamis/comet/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rpamis/comet

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 comet AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rpamis/comet/agents-md/github.svg)](https://agentmods.dev/instructions/rpamis/comet/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rpamis/comet/agents-md"><img src="https://agentmods.dev/badge/instructions/rpamis/comet/agents-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 comet AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rpamis/comet/agents-md"><img src="https://agentmods.dev/badge/instructions/rpamis/comet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,833 This file is loaded in full into every session.
When invoked 6,833 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 $0.06833 $0.06833
Opus 5.5 $0.02733 $0.02733
Sonnet 5.5 $0.01367 $0.01367
Haiku 4.5 $0.00683 $0.00683

Measured 9d ago against content hash f7ef080e87c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

comet 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 9d 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.

AGENTS.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

回复语言

必须采用中文回答用户

表达与文档风格

适用于回复、Skill、开发文档、CLI 帮助、错误提示和代码注释。

  • 使用自然、具体的表达,先说明结果或动作,再说明必要的原因和条件。Skill 指令写清何时执行、执行什么、完成条件是什么。
  • 用事实、行为和例子解释问题;删去空泛评价、宣传口吻、机械排比、重复总结,以及没有实际区别的“不是 X,而是 Y”句式。标题、加粗和列表只用于帮助阅读。
  • 用准确的常用词表达概念,避免堆砌抽象名词、自造口号或生硬直译。技术术语确有必要时保留,并在首次出现且读者可能不熟悉时简要解释。
  • 网站中文内容中,表示 Docker 容器所在机器时保留“宿主机”;其他语境禁用“宿主”一词,根据实际对象使用“Agent 平台”“Agent”“执行器”或“本机”等准确名称。
  • 精简重复表述,保留需求范围、触发条件、例外、失败处理、确认要求和验收标准。必要内容移到参考文件时,写明读取条件与位置;不能以减少字数代替完整说明。

Skill 触发表述规范

修改 skill 时,新增或调整依赖 skill 的触发方式必须和既有写法保持一致:

  • 中文统一使用:**立即执行:** 使用 Skill 工具加载 <skill-name> 技能。禁止跳过此步骤。
  • 英文统一使用:**Immediately execute:** Use the Skill tool to load the <skill-name> skill. Skipping this step is prohibited.
  • 后续输入、上下文或执行要求写在“技能加载后 / After the skill loads”段落,不要把 ARGUMENTS、fast-forward 等另一套调用术语混入触发句。

代码与 CLI 术语

  • 新增或修改命令、参数、函数、类型、模块和协议字段时,先查仓库中同一概念的既有名称,再参考相关 Agent 工具、依赖库或开源项目的公开接口与文档。优先采用含义一致、已有使用惯例的名称。
  • Agent 概念和架构术语应与实际职责对应,例如 tool、agent、session、handoff、checkpoint、router、adapter、state machine;不能仅为显得专业而套用术语或引入对应抽象。不确定是否通用时先核对来源,不凭印象声称是行业标准。
  • 同一概念在代码、CLI、JSON、帮助和文档中保持一致;不同职责保留区别,不为统一名称而混淆状态或角色。CLI 动作使用明确的动词,参数说明操作对象或选项含义,遵循仓库已有命令结构。
  • 没有合适通用词时,使用能直接说明职责的领域名称,并简要定义。现有公开名称的调整须评估兼容性和迁移影响;本规则不要求批量重命名已有接口或重构架构。

项目配置决策

新增 .comet/config.yaml 字段前,先核对当前解析、生成和更新逻辑,以及 Git 历史中已移除的同类字段;Issue 的建议不能单独作为恢复配置的依据。Native v4 已停止在项目配置中维护 native.snapshot 的文件数、字节数等预算,因此生成输入检查也不得换名新增同类项目级限额。检查应流式读取并绑定实际输入;读取失败或不稳定时报告快照不完整,禁止复用旧检查。确需恢复公开预算配置时,先明确用户需求并评估兼容性与迁移影响。

开发工作区保护

开始修改前检查当前分支、比较基线、未提交文件和子模块状态。保留所有无关修改,不得通过 reset、clean、删除或格式化无关文件来换取检查通过。提交时只显式暂存本任务文件。

website 是独立 Git 子模块;只有任务明确涉及网站时才能修改其内容或引用状态。

.agents/skills/comet*、.claude/skills/comet*、平台安装目录和测试生成目录是本地安装或 dogfood 副本,不是产品源码。产品行为应修改 app/、domains/、platform/、assets/ 或对应构建脚本。

分层开发规则

修改目标文件前,读取从仓库根到该文件目录沿途的 AGENTS.md;路径更深的文件补充或覆盖上层规则。.claude/rules/*.md 是 Claude Code 的对应路径规则,.codex/rules/*.rules 只用于 Codex 命令执行策略,不承载开发行为说明。

规则文件的数字前缀只用于分组和稳定排序,不表示优先级。发生冲突时按平台自身的作用域规则处理,不根据编号判断覆盖关系。

问题证据与验证结论

Issue、Review 意见、Project Knowledge、Memory 和历史记录只提供调查线索。可能变化的事实必须在当前分支重新核对;行为缺陷应先在最小临时项目、对应发布包或真实 Runtime 中复现。

Read the full file on GitHub · 331 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. 9d ago Changed · +21 lines · +964 tokens per session f7ef080e87c8
  2. 15d ago Changed · +27 lines · +817 tokens per session 73bb0e700c60
  3. 1mo ago Changed · +8 lines · +142 tokens per session 6f8fbbfd9eb8
  4. 1mo ago Changed · +20 lines · +767 tokens per session bd9b8912a003
  5. 2mo ago Changed · +20 lines · +423 tokens per session dca90d2d98dc
  6. 2mo ago Changed · +16 tokens per session 648ae9942ee0
  7. 2mo ago First seen · 235 lines · 3,704 tokens per session scan A 981953340ffd

Subscribe to this mod's changes

comet AGENTS.md is an instructions file published in the GitHub repository rpamis/comet (3,274 stars, last pushed yesterday), licensed MIT. It adds 6,833 tokens to every session, about $0.0273 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.

Related

comet AGENTS.md compared with instructions from other repositories

comet AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
comet AGENTS.mdrpamis/cometInstructions file3.3kyesterdayMITA6,833Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode