Thermos

by cursorccb5507cec15No license10K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

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.

Instructions onlySoftware Development
AI-generated overview

Runs two parallel code review subagents and synthesizes their findings into one prioritized verdict.

What it does
This skill orchestrates two review passes as parallel background subagents: one covering bugs, breakages, security, developer-experience regressions and feature-flag leaks, and one covering maintainability, structure, file-size growth, spaghetti and abstraction health. It gathers the diff and context, passes the same scoped material to both reviewers, then merges their results into a deduplicated, prioritized set of findings with file references. The output is a unified verdict that weights overlapping findings more heavily and notes remaining uncertainty.
When to use it
Use it for a combined bug, security and code-quality audit of a branch, pull request or set of changed files. It fits requests described as thermos or double thermo review, where two independent review perspectives should be run and reconciled.
Requirements
No scripts are shipped; it is instructions only. It requires an agent environment that supports launching the named subagent types as asynchronous background tasks.

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.

Source and attribution

Source:cursor/pluginsinthermos/skills/thermosat commitccb5507

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Thermos Agent Skill | SourceWeft