task-passport: Instructions file for Codex

AGENTS.md

task-passport AGENTS.md is an instructions file for Codex, OpenCode from dongsheng123132/task-passport. It costs 1,414 tokens per session, scanned A, original, MIT.

Project instructions for Task Passport and TaskPack, two ways to preserve and move work state between coding sessions or machines. A passport is versioned shared state; a TaskPack is a self-contained offline file for handover.

In plain words
What is it for?
Use them to open task state, record checkpoints with version checks, package work for transfer, unpack it on another machine, run repository checks, and rebuild the documentation site.
Why use it?
They prevent one session from silently overwriting another and make clear which facts were verified on the original machine. This helps the next agent distinguish verified information from facts that must be checked again.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is dongsheng123132/task-passport's own configuration. It tells Codex and OpenCode how to work on task-passport 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 task-passport configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dongsheng123132/task-passport. 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/dongsheng123132/task-passport/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dongsheng123132/task-passport

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 task-passport AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dongsheng123132/task-passport/agents-md.svg)](https://agentmods.dev/instructions/dongsheng123132/task-passport/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dongsheng123132/task-passport/agents-md"><img src="https://agentmods.dev/badge/instructions/dongsheng123132/task-passport/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,414 This file is loaded in full into every session.
When invoked 1,414 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 $0.01414 $0.01414
Opus 5 $0.00707 $0.00707
Sonnet 5 $0.00283 $0.00283
Haiku 4.5 $0.00141 $0.00141

Measured 7d ago against content hash a7ae91e0974d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

task-passport 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 7d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-passport / TaskPack — 开机文档

在这个目录开终端的第一件事:打开护照,不要读聊天记录。

护照 TP-3XZB-X84A  —— 本仓库的常驻状态

MCP 已在 .mcp.json 里配好(task_passport_open);没有 MCP 时用 node cli.js open TP-3XZB-X84A。改状态走 checkpoint 并带 expected_version—— 它会拒绝陈旧版本,而不是静默盖掉另一个终端。

这是什么

两个东西,一个仓库,别混着叫

是什么 形态
Task Passport 常驻状态:有版本、有锁、留在 store 里,跨会话跨 harness 活的原件
TaskPack 一次搬运:单文件、自包含、离线、在别人机器上打开 出门的包

护照 --pack--> TaskPack --unpack/land--> 护照。两种编码:.taskpack(BagIt + zip,正本) 与 .taskpack.json(扁平、零安装,首次交接一律用这个)。

规范正本在 docs/taskpack-0.1.md,站点是 https://taskpack.org(由 site/build.mjsdocs/ 生成)。

最原创的那一条(别改掉它)

机器级事实在「打包时」就封存为未证,并记下 verified_on 降级发生在打包端,不是落地端——安全属性必须长在文件里,不能长在接收方的实现上。 一个接手的 AI 拿到包,应该看见「这 10 条在原机器验过、在你这儿不成立」,而不是十个绿勾。

配套的一条:让事实失效的不只有「换了机器」,还有「够不着」。前者靠重验,后者靠开目录, 混为一谈会误导下一个接手的人。

常用命令

npm test          # 47 项,多数是反向用例
npm run check     # 语法检查全部入口文件
npm run pack:check
node cli.js doctor --store <dir>    # 会告警两个权威 store 同时在线
node site/build.mjs                 # 站点从 docs/ 重建,构建会拒绝发布破损声明

当前状态摘要(详细版在护照里,以护照为准)

  • mainorigin/main 同步,taskpack.org 三个端点 200。
  • npm 上 latest 已经是 0.3.0(2026-08-16 以 npm view task-passport version 实查)。 「文档说有、npm 上没有」这个缺口已经关闭。发布状态只以 npm view 为准,CI 绿灯不算数。
  • 工作区有未提交改动,两块:回执合并 land --into。它顺带暴露并修掉一个上游缺口:pack 从前不把提出的 ask 记进护照,于是回执回来时无处可归、只能人工重录;现在 pack 会写回护照(幂等, 内容没变不撞版本),输出里带 asks_recorded。 ② 发件台账 outbox.js + task-passport outbox。每次 pack 追加一行 JSONL 并存一份 当时那份护照的存根(存的是封存后、真出门的那版)。回答「上周发给客户的那个包里到底有什么」。 存根文件名带包的 sha256 前 8 位——没有它,同一版同一秒打两个包会撞名互相覆盖(冒烟时抓到的)。 台账不是公证,能写 store 的人就能改它,README 里写明了这一条。 测试 78/78,新增 test/merge-receipt.test.mjs(18) 与 test/outbox.test.mjs(12),逐项变异验证过。
  • 三机实测过(2026-08-16):两台 macOS + 一台 Windows Server,conformance 各 10/10、 附件字节全一致、封存规则双向有效。手填回执若加一条自己机器的事实并标 verified,会掉 C0—— 落地宽容、判定严格,属预期行为,但要在给客户的说明里讲清楚。
  • 本地分支 fix/windows-bom-and-store-guardrails 领先 main 8 个 commit 且没有远端副本。 内容已以别的 commit 进了 main。不要 push 它:它的历史里 commit 了 docs/STRATEGY.md, 而那份文件在 main 上是被 .gitignore 明文排除的内部判断。
  • 工作区 3 个 .tp-*.mjs 是另一个终端留下的未跟踪探针,不属于任何提交。

Read the full file on GitHub · 75 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. 7d ago First seen · 75 lines · 1,414 tokens per session scan A a7ae91e0974d

Subscribe to this mod's changes

task-passport AGENTS.md is an instructions file published in the GitHub repository dongsheng123132/task-passport (11 stars, last pushed 12d ago), licensed MIT. It adds 1,414 tokens to every session, about $0.0071 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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 · 6,785 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 · 7,296 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens