mcpField
T
thermos

thermos

github.com/michael-denyerTesting & quality3.6k229 installsUpdated today
Repository

About thermos

thermos is a code-review skill for Codex, GitHub Copilot, and Muse. It runs two parallel review passes—one for defects and risks, another for maintainability—and combines their findings.

Key features

  1. 01Parallel bug and risk review
  2. 02Parallel code-quality review
  3. 03Scope reviews to relevant changes
  4. 04Deduplicate and prioritize findings

Use cases

  1. 01Audit a branch or pull request
  2. 02Find bugs and security risks
  3. 03Review maintainability and code structure

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/michael-denyer/pstack-claude --skill thermos

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

Details

From the project README

Thermos

On Codex, read the platform mapping, including its per-skill notes, before following this skill.

On GitHub Copilot, read the platform mapping, including its per-skill notes, before following this skill.

On Muse, read the platform mapping, including its per-skill notes, before following this skill.

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: "pstack:thermo-nuclear-review-subagent" for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.
    • subagent_type: "pstack: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