Borrowing it
Nothing to install: this file belongs to liujuanjuan1984/codex-a2a. 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/liujuanjuan1984/codex-a2a/main/AGENTS.mdgit clone --depth 1 https://github.com/liujuanjuan1984/codex-a2aWrote 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/liujuanjuan1984/codex-a2a/agents-md)<a href="https://agentmods.dev/instructions/liujuanjuan1984/codex-a2a/agents-md"><img src="https://agentmods.dev/badge/instructions/liujuanjuan1984/codex-a2a/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 | $0.01097 | $0.01097 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
codex-a2a 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 6d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
以下规范适用于当前仓库内的 coding agent 协作与交付流程。
1. 核心原则
- 在保证安全、可追踪的前提下推进任务,避免不必要的流程阻断。
- 保持与现有仓库结构、实现风格和工程习惯一致。
2. Git 工作流
- 禁止直接向受保护分支提交或推送:
main/master/release/*。 - 每项开发任务应在独立分支实施,建议从最新主干切出。
- 同步主干优先使用
git fetch+git merge --ff-only,避免隐式合并。 - 允许将开发分支推送到远端同名分支,便于协作与备份。
- 禁止改写公共历史:
git push --force、git push --force-with-lease、随意rebase。 - 仅提交本次任务相关文件,不清理或回滚与任务无关的在地改动。
3. Issue 与 PR 协作
- 开发类任务开始前,先检查是否已有相关 open Issue(例如
gh issue list --state open)。 - 若无相关 Issue,应创建新 Issue 跟踪;Issue 建议包含背景、复现步骤、预期/实际、验收标准,并附
git rev-parse HEAD快照。 - 仅协作规范/流程文档改动(如
AGENTS.md)可直接修改,无需额外创建 Issue。 - Issue 标题前缀建议使用
[feat]、[bug]、[docs]、[ops]、[chore]。 - 提交信息若服务于某个 Issue,应在 commit message 中标注对应
#issue。 - PR 默认建议创建为 Draft,并在描述中标明关联关系(如
Closes #xx/Relates to #xx)。 - 出现关键进展、方案变化或新风险时,及时在对应 Issue/PR 中同步,避免重复评论。
4. 工具与文本规范
- 读写 Issue/PR 使用
ghCLI,不通过网页手工编辑。 - 务必不要使用 Codex GitHub 连接器(包括但不限于任何 GitHub MCP / connector / app 方式);任何时候只允许通过
ghCLI 操作 Issue、PR、评论与相关元数据。 - 若
ghCLI 遇到权限、认证、网络策略或仓库策略障碍,必须停止继续尝试,并向人类说明阻塞点,由人类提供帮助或代为执行;不得改用 Codex GitHub 连接器兜底。 - Issue、PR 与评论使用简体中文;专业术语可保留英文。
- 多行正文先写入临时文件,再用
--body-file传入;不要在--body中拼接\\n。 - 同仓引用使用
#123自动链接;跨仓引用使用完整 URL。
5. 回归与验证
- 回归策略按改动类型选择;默认基线为:
bash ./scripts/validate_baseline.sh
- Before committing, complete the required validation for the current change set; by default, run the baseline checks above before creating a commit.
- Before creating or updating a PR, confirm the relevant local validation has passed so CI is not left to catch issues that are already reproducible locally.
pre-commit若自动修复文件(如ruff --fix),需复查改动后再提交。- If
pre-commitmodifies files, include those changes in the same commit and rerunuv run pre-commit run --all-filesuntil it completes without further rewrites. - After running
pre-commit, inspectgit status --shortbefore committing or pushing; do not assume hook-made rewrites are already included in the pending commit. - Do not push or update a PR while the working tree still contains hook-generated edits from the latest
pre-commitrun. - Shell/部署脚本改动:在基线之外,至少执行
bash -n对改动脚本做语法校验。 - 文档-only 改动:可不跑测试,但应自检命令与路径示例可用。
uv sync --all-extras仅在首次初始化或依赖变更时需要,不作为每次改动必做项。- 若受环境限制无法完成某项验证,必须在汇报中明确说明未执行项与原因。
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.
- 6d ago First seen · 58 lines · 1,097 tokens per session scan A 529f69776aa6
codex-a2a AGENTS.md is an instructions file published in the GitHub repository liujuanjuan1984/codex-a2a (14 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,097 tokens to every session, about $0.0055 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
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.