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.
npx skills add luis-at-safebase/luism-claude-plugins --skill sentinelgit clone --depth 1 https://github.com/luis-at-safebase/luism-claude-pluginsWrote 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/skills/luis-at-safebase/luism-claude-plugins/sentinel)<a href="https://agentmods.dev/skills/luis-at-safebase/luism-claude-plugins/sentinel"><img src="https://agentmods.dev/badge/skills/luis-at-safebase/luism-claude-plugins/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.
<a href="https://agentmods.dev/skills/luis-at-safebase/luism-claude-plugins/sentinel"><img src="https://agentmods.dev/badge/skills/luis-at-safebase/luism-claude-plugins/sentinel.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 | $0.00057 | $0.03845 |
| Opus 5 | $0.00028 | $0.01922 |
| Sonnet 5 | $0.00011 | $0.00769 |
| Haiku 4.5 | $0.00006 | $0.00384 |
Grade A, and why
sentinel 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 11d 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User's request: $ARGUMENTS
sentinel — UI artifact generator
You generate visual QA artifacts: a set of screenshots and a GIF that shows the feature working in the browser. You operate in two modes depending on what the user provides.
Step 0: Parse arguments
Extract from $ARGUMENTS:
debug— optional flag, present if--debugappears in argsfolder— optional custom artifact folder name, value after--folder(e.g.--folder abc→folder="abc")- Everything else is either a PR number or freeform instructions
Determine mode:
-
If the remaining argument is a bare integer (e.g.
22254) → PR mode -
If the remaining argument is absent or non-numeric free text (e.g. "toggle dark mode 3 times…") → Manual mode
-
If nothing is provided at all → ask:
PR number or freeform instructions?
Reply with a PR number (e.g.
22254) to capture a pull request, or describe what you want navigated (e.g. "go to settings and toggle dark mode").
Store screenshot_flag based on debug:
debugpresent →screenshot_flag="--annotate"(numbered red boxes, useful for inspecting what sentinel saw and clicked)debugabsent →screenshot_flag=""(clean screenshots)
Use screenshot_flag on every agent-browser screenshot call throughout the run:
agent-browser screenshot $screenshot_flag "$ARTIFACT_DIR/step-001.png"
Step 1: Preflight checks
Run these in parallel:
which agent-browser 2>/dev/null || echo "MISSING"
which magick 2>/dev/null || echo "MISSING_IMAGEMAGICK"
If agent-browser is missing, tell the user:
agent-browseris not installed. Runnpm install -g [email protected] && agent-browser installthen retry.
Exit.
If imagemagick is missing, warn but continue — GIF generation will be skipped:
ImageMagick not found. Will deliver screenshots only (no GIF). Install with
brew install [email protected]to enable GIF output.
Step 2: Build navigation plan
PR mode
gh pr view <pr_number> --json title,body,headRefName,files --jq '{title: .title, body: .body, branch: .headRefName, files: [.files[].path]}'
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.
- 11d ago First seen · 422 lines · 0 tokens per session scan A b62289228c55
sentinel is a skill published in the GitHub repository luis-at-safebase/luism-claude-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 3,845 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…