mcpField
T
thermos

thermos

github.com/ilteooodTesting & quality2191 installsUpdated 4d ago
Repository

About thermos

A workflow that runs two specialized code-review subagents in parallel, then synthesizes their findings. It separates branch risks such as bugs and security issues from code-quality concerns such as maintainability and structure.

Key features

  1. 01Determines review scope and gathers context
  2. 02Runs two review subagents in parallel
  3. 03Checks bugs, security, and branch risks
  4. 04Reviews structure and maintainability
  5. 05Deduplicates and prioritizes findings

Use cases

  1. 01Review a pull request using two focused passes
  2. 02Audit changed files for risks and code quality
  3. 03Combine overlapping reviewer findings into a verdict

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ilteoood/harness --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