A security workflow for reviewing add-ons, intercepting dependency installations, checking project packages for vulnerabilities, and inspecting system security. A dependency is an external package that a project relies on.

It helps vet skills from external sources, inspect installation commands, audit project dependencies, and run system security checks manually or on a schedule.

It helps identify unsafe add-ons, risky package installations, project vulnerabilities, and broader system security problems before they cause harm.

sentinel — Skill for Claude Code by guihai24/openskills

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.

Any agent

npx skills add guihai24/openskills --skill sentinel

Clone the repo

git clone --depth 1 https://github.com/guihai24/openskills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/guihai24/openskills/sentinel/github.svg)](https://agentmods.dev/skills/guihai24/openskills/sentinel)

Your own site

<a href="https://agentmods.dev/skills/guihai24/openskills/sentinel"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/sentinel/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/guihai24/openskills/sentinel"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,887 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.02887
Opus 5.5	$0.00028	$0.01155
Sonnet 5.5	$0.00014	$0.00577
Haiku 4.5	$0.00007	$0.00289

Measured 2mo ago against content hash 690eb72da4da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

sentinel scanned grade B 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.

The scan reads SKILL.md. This mod also ships 6 executable files (hooks/sentinel-pre-install.sh, scripts/audit-deps.sh, scripts/check-package.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

• Requesting sudo privileges

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to `~/.claude/settings.json`:

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

• curl/wget to unknown URLs

skills/sentinel/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentinel — Unified Security Protection

All security capabilities in one place. 4 modules, automatic triggers, users only make traffic-light decisions.

Module Overview

Module	Function	Trigger
M1	Skill security review	Auto-triggered before skill installation
M2	Dependency install interception (3-layer)	PreToolUse + PostToolUse Hook
M3	Project dependency audit	`/sentinel check` or periodic
M4	System security inspection	`/sentinel audit` or daily cron

M1: Skill Security Review

Inherits all skill-vetter capabilities + enhancements

Trigger

User requests to install a skill (from ClawdHub, GitHub, or other sources), or agent detects skill installation intent.

Step 1: Source Verification

Answer the following:

Source? (ClawdHub / GitHub / other)
Is the author well-known / trusted?
Star count / download count?
Last updated?
Any user reviews?

Step 2: Code Review (mandatory)

Read all files in the skill. Check against the following red-line checklist (any match → flag immediately):

Base Red Lines (inherited from skill-vetter)

🚨 Flag on match:
─────────────────────────────────────────
• curl/wget to unknown URLs
• Sending data to external servers
• Requesting credentials/tokens/API keys
• Reading ~/.ssh, ~/.aws, ~/.config (without clear justification)
• Accessing MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• Using base64 decode
• Using eval()/exec() on external input
• Modifying system files outside workspace
• Installing undeclared packages
• Network calls using IP addresses instead of domains
• Obfuscated code (compressed, encoded, minified)
• Requesting sudo privileges
• Accessing browser cookies/sessions
• Touching credential files

Enhanced Red Lines (sentinel additions)

🚨 Additional checks:
─────────────────────────────────────────
• Contains .pth files
• Large base64/hex encoded content (>100 chars)
• Modifies CLAUDE.md or settings.json (privilege escalation)
• Registers Claude Code Hooks (can hijack other operations)
• scripts/ contains network calls (curl, wget, fetch, requests)
  → Check target URLs against known-malicious.md
• Introduces external dependencies → chain to M2 for each dependency

Read the full file on GitHub · 349 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 349 lines · 70 tokens per session scan B 690eb72da4da

Subscribe to this mod's changes

sentinel is a skill published in the GitHub repository guihai24/openskills (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,887 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 3 findings (asks for root, 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.