Borrowing it
Nothing to install: this file belongs to xiaolai/claudepot-app. 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/xiaolai/claudepot-app/main/AGENTS.mdgit clone --depth 1 https://github.com/xiaolai/claudepot-appWrote 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/xiaolai/claudepot-app/agents-md)<a href="https://agentmods.dev/instructions/xiaolai/claudepot-app/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/claudepot-app/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/xiaolai/claudepot-app/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/claudepot-app/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 | $0.05302 | $0.05302 |
| Opus 5.5 | $0.02121 | $0.02121 |
| Sonnet 5.5 | $0.01060 | $0.01060 |
| Haiku 4.5 | $0.00530 | $0.00530 |
Grade A, and why
claudepot-app 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 4d 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudepot
Control center for Claude Code and Claude Desktop. Tauri 2 + Rust + React: accounts, projects, sessions, API keys, third-party providers, agents, memory files, usage and cost, updates, notifications and a LAN remote panel, under one shell with tray and menubar.
The domain model is five nouns — account, cli, desktop,
project, agent. Every other surface is a presentation layer or a
behaviour over those nouns and over CC's filesystem. Do not add a noun
casually (.claude/rules/architecture.md); that limit is on the domain
model, not on what the UI may expose.
How the docs are split
This file is @-included into every session, so it holds commands,
layout and the rules that must not be broken, in a line or two each.
docs/notes/ carries the reasoning: what was measured, which obvious
alternative was tried and reverted, and which shipped bug each rule was
written after. Notes are read on demand; they are not optional.
| Note | Read it before changing |
|---|---|
data-dir.md |
anything in ~/.claudepot/ — the store inventory and each file's contract |
gui-shell.md |
the Tauri shell, the section registry, the ⌘K palette, event channels, the session index |
cc-integration.md |
retention, permission grants, peer messaging, CC env variables, any write to a CC settings file |
remote-control.md |
claudepot-core::remote, panel/, approving from the phone |
relay.md |
claudepot-core::relay, claudepot relay, Settings → Relay |
core-modules.md |
pricing, the env vault, auto-rotation, token refresh, the corpus |
i18n.md |
any user-facing string or catalog |
test-gates.md |
a check:* gate, and especially before relaxing one |
assets-and-release.md |
icons, screenshots, git hooks, release validation |
web.md |
web/ (claudepot.com) |
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.
- 4d ago Changed · +6 lines · +114 tokens per session 9aee2a42147c
- 6d ago Changed · +26 lines · +390 tokens per session 5312b86fe737
- 1mo ago Changed · -941 lines · -15,138 tokens per session scan D → A 909c4cb09043
- 1mo ago Changed · +63 tokens per session e572bb79948d
- 1mo ago Changed · -1,363 lines · -18,109 tokens per session 731f57c45e61
- 2mo ago Changed · +289 lines · +4,386 tokens per session 9c94eac6cc29
- 2mo ago First seen · 2,388 lines · 33,596 tokens per session scan D 41f17222c1aa
claudepot-app AGENTS.md is an instructions file published in the GitHub repository xiaolai/claudepot-app (127 stars, last pushed 2d ago), licensed ISC. It adds 5,302 tokens to every session, about $0.0212 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.
claudepot-app AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claudepot-app AGENTS.mdxiaolai/claudepot-app | Instructions file | 127 | 2d ago | ISC | A | 5,302 | Claude Code, Codex, OpenCode |
| vibe-coding-prompt-template backend.instructions.mdKhazP/vibe-coding-prompt-template | Instructions file | 3.2k | 1mo ago | MIT | A | 139 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |