agentmods.dev

claude-code-sentinel AGENTS.md

A project guide for AI coding agents working on Claude Code Sentinel, a native macOS companion that handles Claude Code permission prompts, questions, and completion notifications.

In plain words
What is it for?
Use it when modifying Sentinel’s Swift code, build process, documentation, installer, release workflow, or terminal-notification behavior.
Why use it?
It gives the agent the project context and rules needed to change the code safely without guessing how the app works.

Instructions file for CodexOpenCode

4 2mo ago D scan 1,374 tokens original MIT
View the source file hlongc/claude-code-sentinel
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/hlongc/claude-code-sentinel/agents-md
Clone the repo
git clone --depth 1 https://github.com/hlongc/claude-code-sentinel

Made for: Codex, OpenCode.

Per session 1,374 This file is loaded in full into every session.
When invoked 1,374 The same file — it is already loaded in full.
Security scan D 3 findings. Scan, not verified.
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 $0.01374 $0.01374
Opus 5 $0.00687 $0.00687
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00137 $0.00137

Measured 2d ago against content hash 93e978f270b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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
AGENTS.md · 230 lines

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.md and README.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, or allow with updatedPermissions.
    • Button labels map to Yes, Yes, don't ask again, and No.
  • PreToolUse for AskUserQuestion
    • 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.

Read the full file on GitHub · 230 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. 2d ago First seen · 230 lines · 1,374 tokens per session scan D 93e978f270b4

Subscribe to this mod's changes

claude-code-sentinel AGENTS.md is an instructions file published in the GitHub repository hlongc/claude-code-sentinel (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0069 per session on Opus 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.

ai-codingclaude-codeclaude-code-hooksdeveloper-toolsnotificationsopencode
Related

Other instructions, from other repositories

agent-of-empires AGENTS.md

AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.

agent-of-empires/agent-of-empires · 1,165 tokens

opencode-claude-memory AGENTS.md

Instructions for kuitos/opencode-claude-memory, covering agents.md, structure, where to look, critical coupling and conventions.

kuitos/opencode-claude-memory · 1,713 tokens

armada AGENTS.md

Instructions for rafmacalaba/armada, covering armada — build rules, the job, the team, repository conventions and adaptive delivery.

rafmacalaba/armada · 1,423 tokens

opm AGENTS.md

Instructions for tbcrawford/opm, covering project, command api, constraints, technology stack and conventions.

tbcrawford/opm · 1,573 tokens

Throughline AGENTS.md

Instructions for kitepon/Throughline, covering agents.md, 最初に読むもの, 製品の所有境界, claude 正本を守る and codex 作業方針.

kitepon/Throughline · 2,267 tokens

ninthwave CLAUDE.md

Instructions for ninthwave-io/ninthwave, covering ninthwave, development, architecture, conventions and test safety.

ninthwave-io/ninthwave · 1,812 tokens