mcpField
T
thermos

thermos

github.com/potetoTesting & quality12954 installsUpdated 21w ago
Repository

About thermos

A skill that runs two thermo review passes in parallel through background subagents, then combines their findings. One pass examines branch risks such as bugs and security; the other focuses on maintainability and codebase health.

Key features

  1. 01Determine review scope and gather context
  2. 02Run two review subagents in parallel
  3. 03Check branch risks and security
  4. 04Assess maintainability and codebase health
  5. 05Deduplicate and prioritize findings

Use cases

  1. 01Review a pull request diff
  2. 02Audit changes on the current branch
  3. 03Find security or development-experience regressions
  4. 04Assess structure and maintainability risks

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/poteto/plugins --skill thermos

After installing, type/thermosin Claude Code to confirm it loaded.

Details

From the project README

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.

Comments

Markdown supported