Thermos
Spins up two specialized review subagents in parallel: one hunts for bugs, security holes, and feature-flag leaks, while the other focuses on code quality, maintainability, and structural debt. Both run async in the background on the same diff, then their findings get deduplicated and synthesized with overlapping concerns weighted higher. The workflow is pretty prescriptive about gathering context upfront and keeping the final summary tight, which matters when you're already looking at two full review passes. Useful when you want comprehensive branch audit coverage without running reviews sequentially or when a PR touches enough surface area that you'd rather parallelize the paranoia.
- skills.sh installs
- 2.3K
- GitHub stars
- 15.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add cursor/plugins --skill thermos --agent claude-codeInstalls into .claude/skills of the current project.
Files
Thermos
Run the two thermo review passes as async background subagents in parallel, then synthesize their results.
Workflow
- Determine the review scope from the user request, PR, current branch, or relevant changed files.
- Gather the diff and any file/context excerpts needed for reviewers to evaluate the change without guessing.
- Launch both subagents in the same message with
run_in_background: true:subagent_type: "thermo-nuclear-review-subagent"for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.subagent_type: "thermo-nuclear-code-quality-review-subagent"for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.
- Pass each subagent the same scoped diff/file context and ask it to return prioritized findings with file references and evidence.
- After both finish, synthesize the results with findings first, deduplicated across reviewers. Weight overlapping findings more heavily, resolve disagreements with your own judgment, and keep summaries brief.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/cursor/plugins
- Categories
- Git & Pull Requests, Code Review & Quality, Automation & Workflows
- First seen
- Jun 23, 2026
More from cursor/plugins
All 47- New Branch And Pr2.2K
- Run Smoke Tests2.2K
- Workflow From Chats2.2K
- Poteto Mode1.6K
- Continual Learning1.5K
- Cli For Agents1.4K
- Cursor Sdk1.3K
- Orchestrate1.2K
- Docs Canvas1.2K
- Create Plugin Scaffold1.2K
- Review Plugin Submission1.2K
- Ralph Loop1K
- Create Learning Path1K
- Run Learning Retrospective925
- Check Agent Compatibility4
- Unslop34.1K
- Thermo Nuclear Code Quality Review23.9K
- Deslop10.2K
- Typescript Best Practices10K
- Blast Radius7.1K
- How6.7K
- Why6.5K
- Arena5.7K
- Architect5.6K
Recommended
More Git & Pull Requests1
qavinvcn/mattpocock-skills-zh-cn交互式 QA 会话，用户以对话方式报告缺陷或问题，代理创建 GitHub issues。后台探索代码库以获取上下文和领域语言。适用于用户想报告缺陷、执行 QA、以对话方式提交 issues，或提到 “QA session” 时。2.1Kskills.sh installs
qavinvcn/mattpocock-skills-zh-cn交互式 QA 会话，用户以对话方式报告缺陷或问题，代理创建 GitHub issues。后台探索代码库以获取上下文和领域语言。适用于用户想报告缺陷、执行 QA、以对话方式提交 issues，或提到 “QA session” 时。2.1Kskills.sh installs2
what-if-oraclek-dense-ai/scientific-agent-skillsRun structured What-If scenario analysis with 4–6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order). Use when the user a2.1Kskills.sh installs
what-if-oraclek-dense-ai/scientific-agent-skillsRun structured What-If scenario analysis with 4–6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order). Use when the user a2.1Kskills.sh installs3
nemo-rl-session-memorynvidia/skillsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-ru2.1Kskills.sh installs
nemo-rl-session-memorynvidia/skillsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-ru2.1Kskills.sh installs4
flutter-adaptive-uimadteacher/mad-agents-skillsBuild, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use whe2Kskills.sh installs
flutter-adaptive-uimadteacher/mad-agents-skillsBuild, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use whe2Kskills.sh installs5
od-contributenexu-io/open-designOne-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; 1.9Kskills.sh installs
od-contributenexu-io/open-designOne-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; 1.9Kskills.sh installs6autoskillk-dense-ai/scientific-agent-skillsObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or comp1.9Kskills.sh installs
autoskillk-dense-ai/scientific-agent-skillsObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or comp1.9Kskills.sh installs