Security · Testing / AGENT SKILL

thermos

1.7K installs 8.5K GitHub stars

Run two review subagents in parallel and combine their bug, security, and code-quality findings.
Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

One new superpower.

Run this command in your project to choose an agent and install the skill.

npx skillycli add https://github.com/cursor/plugins --skill thermosView original source

BEFORE YOU INSTALL

Understand the trade-offs.

SECURITY REVIEW

Not yet assessed

Review the original instructions and requested permissions before installing.

No security review is available for this catalog entry yet.

SKILL QUALITY

Not yet assessed

How clearly the skill guides your agent, how complete its workflow is, and how you can check the outcome.

No quality assessment is available for this catalog entry yet.

The full skill.

Original instructions from the publisher’s SKILL.md

# 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 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.
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.