Borrowing it
Nothing to install: this file belongs to hlongc/claude-code-sentinel. 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/hlongc/claude-code-sentinel/main/AGENTS.mdgit clone --depth 1 https://github.com/hlongc/claude-code-sentinelWrote 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/hlongc/claude-code-sentinel/agents-md)<a href="https://agentmods.dev/instructions/hlongc/claude-code-sentinel/agents-md"><img src="https://agentmods.dev/badge/instructions/hlongc/claude-code-sentinel/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/hlongc/claude-code-sentinel/agents-md"><img src="https://agentmods.dev/badge/instructions/hlongc/claude-code-sentinel/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 | $0.01374 | $0.01374 |
| Opus 5.5 | $0.00550 | $0.00550 |
| Sonnet 5.5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade D, and why
claude-code-sentinel AGENTS.md scanned grade D with 3 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 2mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/hlongc/claude-code-sentinel/main/install.sh | bash Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Avoid leaving duplicate hooks in `~/.claude/settings.json`. Duplicate user-level and managed hooks cause duplicate popovers and duplicate completion notifications. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/hlongc/claude-code-sentinel/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file gives AI coding agents enough project context to work safely and effectively on Claude Code Sentinel.
Project Overview
Claude Code Sentinel is a native macOS companion for Claude Code hooks. It shows lightweight approval popovers for permission prompts, handles AskUserQuestion choices, and sends completion/failure notifications.
The project is intentionally small:
- Main implementation:
Sources/ClaudeCodeSentinel/main.swift - Build entrypoint:
Makefile - User docs:
README.mdandREADME.en.md - Maintainer docs:
docs/maintainer.md - Launch copy:
docs/launch-posts.md - One-line installer:
install.sh - Release workflow:
.github/workflows/release.yml
The generated binary is release/claude-code-sentinel. release/ is ignored by git.
Core Behavior
Sentinel is invoked by Claude Code hooks. It is not a long-running service.
Supported hook paths:
PermissionRequest- Shows a macOS approval popover.
- Returns
allow,deny, orallowwithupdatedPermissions. - Button labels map to
Yes,Yes, don't ask again, andNo.
PreToolUseforAskUserQuestion- Shows one question at a time.
- Returns selected answers through
updatedInput.
Notification- Forwards Claude Code notifications to macOS Notification Center.
Stop- Sends completion notifications.
StopFailure- Sends failure notifications.
It uses Claude Code hooks only. It does not inspect or control arbitrary subprocess prompts inside already-running shell commands.
UI Notes
The popover is built with AppKit in main.swift.
Important UI properties:
- Fixed-width upper-right floating window.
- Content wraps instead of expanding horizontally.
- Window background can be dragged.
- Permission body uses a monospaced text area.
- Active-terminal suppression avoids showing popovers when the user is actively using the Claude terminal.
If editing UI code, verify long titles, long paths, long tool names, and JSON/command bodies do not stretch the window off-screen.
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.
- 2mo ago First seen · 230 lines · 1,374 tokens per session scan D 93e978f270b4
claude-code-sentinel AGENTS.md is an instructions file published in the GitHub repository hlongc/claude-code-sentinel (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0055 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.