Home › AI agent skills › Thermos
CThermos
○ Not reviewed on October 31, 2026 Plugin
Cursor's review plugin. It runs two reviews in parallel on the same branch: one looks for bugs, regressions and security flaws, the other judges code quality and structure. The agent then merges both reports.
Security review
○ Not reviewed
Not yet reviewed with our full method: entry built from the official documentation, a passive reading of the SKILL.md files and manifests, and GitHub metadata of October 31, 2026.
- What it can do: The three skills only run when you call them by name (disable-model-invocation). They read the diff and the changed files and return a report. The security review may read the PR discussion with gh or glab. The plugin description mentions "take-the-wheel" and "FSD merge-ready" flows that we did not find in the folder.
Only the publisher's documentation has been read. Check the permissions you grant when you connect it, and start with read-only access if it is offered.
Install
/add-plugin thermos (Cursor)
Command copied from the official documentation. Read the code before you run it, and prefer a version pinned to a commit or a release.
Similar skills
VLSkill (SKILL.md), official Rust command line tool that drives a browser for AI agents, with a skill to install. The agent opens pages, clicks, fills in forms and reads the result.
- By: Vercel Labs
- Works in: Claude, OpenAI Codex, Cursor, Gemini CLI
- Cost: Free (Apache 2.0 licence)
MCP server and CLI that let the agent control and inspect a live Chrome: performance traces, network requests, console, screenshots. Ships with skills (accessibility, memory leaks, LCP).
- By: Google (Chrome DevTools)
- Works in: MCP servers
- Cost: Free (Apache 2.0 licence)
Official Claude Code plugin: the /code-review command runs 4 agents in parallel on a pull request (CLAUDE.md rules, bugs, git history), scores each issue from 0 to 100 and keeps only those at 80 or more.
- By: Anthropic
- Works in: Claude
- Cost: Free (Apache 2.0 licence)
Plugin by Trail of Bits, a security audit firm. It reviews a change (PR, commit or diff) for security: git history of removed code, number of callers affected, changed code with no test, then a markdown report.
- By: Trail of Bits
- Works in: Claude, OpenAI Codex
- Cost: Free (CC BY-SA 4.0 licence)
MSkill (SKILL.md), official Playwright command line tool, shipped with skills for coding agents. The agent opens a browser, tests pages, takes screenshots and works with Playwright tests.
- By: Microsoft
- Works in: Claude
- Cost: Free (Apache 2.0 licence)
MCP server that gives the agent a browser driven by Playwright. The agent reads the page through the accessibility tree, without screenshots or a vision model.
- By: Microsoft
- Works in: MCP servers
- Cost: Free (Apache 2.0 licence)
You publish a skill or an MCP server? Submit it for free. It is listed as "not reviewed" until we have read its code.
Submit a skill → 🎁 Get the pack: 20 AI prompts to win clients
Free and available right away. Then email tips to pick AI tools for your goal. One-click unsubscribe.