Double pre-merge review of a branch or PR diff: bugs and security plus code quality, via two parallel thermo-nuclear subagents. Use when the user says /thermos, 'double thermo review' or 'audit this branch before merge'. Not for a whole repo (use deep-code-audit).
Installs into .claude/skills of the current project.
Are you the author of Thermos?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/gastonchevarria-thermos)
---
name: thermos
description: "Double pre-merge review of a branch or PR diff: bugs and security plus code quality, via two parallel thermo-nuclear subagents. Use when the user says /thermos, 'double thermo review' or 'audit this branch before merge'. Not for a whole repo (use deep-code-audit)."
---
# Thermos
Run the two thermo review passes as async background subagents in parallel, then synthesize their results.
## Workflow
1. Determine the review scope from the user request, PR, current branch, or relevant changed files.
2. Gather the diff and any file/context excerpts needed for reviewers to evaluate the change without guessing.
3. Launch both subagents in the same message so they run in parallel. Use `run_in_background: true` when the subagent tool supports it (Claude Code); otherwise launch them in the foreground in that same message (Cowork):
- `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.
4. Pass each subagent the same scoped diff/file context and ask it to return prioritized findings with file references and evidence.
5. 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.
If individual background summaries are already visible to the user, do not restate them wholesale. Surface the unified verdict, the highest-signal findings, and any remaining uncertainty.
