mcpField
T
thermo-run

thermo-run

github.com/gannonhTesting & quality2107 installsUpdated 8w ago
Repository

About thermo-run

Thermos is an agent skill that runs two code-review passes in parallel and synthesizes their findings. It covers branch risks as well as maintainability and codebase health.

Key features

  1. 01Determine review scope
  2. 02Gather diffs and relevant context
  3. 03Run two review subagents in parallel
  4. 04Deduplicate and prioritize findings
  5. 05Synthesize a concise verdict

Use cases

  1. 01Review a pull request
  2. 02Audit changes on the current branch
  3. 03Assess maintainability alongside bugs and security risks

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gannonh/skills --skill thermo-run

After installing, type/thermo-runin 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 parallel:
    • /skill:thermo-nuclear-review for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.
    • /skill:thermo-nuclear-code-quality-review 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