Borrowing it
Nothing to install: this file belongs to x0c/corral. 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/x0c/corral/main/AGENTS.mdgit clone --depth 1 https://github.com/x0c/corralWrote 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/x0c/corral/agents-md)<a href="https://agentmods.dev/instructions/x0c/corral/agents-md"><img src="https://agentmods.dev/badge/instructions/x0c/corral/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.
<a href="https://agentmods.dev/instructions/x0c/corral/agents-md"><img src="https://agentmods.dev/badge/instructions/x0c/corral/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.11651 | $0.11651 |
| Opus 5.5 | $0.04660 | $0.04660 |
| Sonnet 5.5 | $0.02330 | $0.02330 |
| Haiku 4.5 | $0.01165 | $0.01165 |
Grade B, and why
corral AGENTS.md scanned grade B with 1 finding 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 22d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **「默认跳过全部权限问询」是本项目的既定产品默认，不是待讨论选项**（机主 2026-08-01 明确拍板）。凡是 corral 拉起运行时的路径——原生恢复、跨运行时接力、空白新建、直启透传，以及未来的命令拦截/shim 入口——都必须自动垫上该运行时的放行参数，让用户拿到的是开箱免打断的体验。新增运行时时，找出并验证它的放行参数属于接入工作的必做项，不是可选增强；找不到就在维护指南里如实记录能力差距，而不是默默留空。放行参数在 How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corral
终端会话接力 CLI，支持跨 Claude Code / Codex / OpenCode / Cursor / Pi 会话恢复与接力（另有 Kimi 兼容实现 dormant：保留、不维护、无界面入口）。
通用工程规范：Python 规范
文档导航
Read the documents whose described content is relevant before deciding or changing behavior.
- Agent workflow: Readiness, resource ownership, resumable delivery and checkpoints.
- Product task routing: Detailed cross-component preconditions and investigation routes.
- CLI instructions: Terminal UI, runtime integration, local development and CLI delivery.
- Apple instructions: Shared iPhone/Mac client, native UI, signing and device delivery.
- Relay instructions: Encrypted relay service, APNs and self-hosting.
- Public presentation: Approved identity, brand assets and sanitized captures.
- Independent UI annotation: Independent EditHere core and optional Corral adapter boundary.
- Remote protocol: Pairing, relay/security boundaries, message delivery and multi-runtime acceptance.
- Mobile data plane: History loading, live data isolation, question state and reconnect recovery.
- Managed session identity: Pi/Codex ownership, claims, plugins and legacy migration.
- Completion notifications: Completed/interrupted evidence, notification preferences, deduplication and delivery.
- Historical multi-agent report: Single-day archive, not current behavior authority.
- UI change-request adapter: Corral's optional adapter for independent UI annotation.
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.
- 22d ago Changed · +9 lines · +376 tokens per session da5ee09cf78a
- 23d ago Changed · -1 lines · -85 tokens per session 3ac45503dbf9
- 24d ago Changed · +3 lines · -7,983 tokens per session c13b506b3e30
- 25d ago Changed · +31 tokens per session d3dea162ff6d
- 28d ago Changed · +12 lines · +247 tokens per session 9e9b509b334d
- 29d ago Changed · -41 lines · -2,693 tokens per session 5d61053595b6
- 1mo ago Changed · +1 lines · +155 tokens per session 1081980e5043
- 1mo ago Changed · +1 lines · +139 tokens per session 35a844172697
- 1mo ago Changed · +101 tokens per session ef3a79691c03
- 1mo ago First seen · 265 lines · 21,363 tokens per session scan B 32c91efe13df
corral AGENTS.md is an instructions file published in the GitHub repository x0c/corral (3 stars, last pushed 22d ago), licensed MIT. It adds 11,651 tokens to every session, about $0.0466 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.