Summary
Spins up two specialized review subagents in parallel: one hunts for bugs, security holes, and feature-flag leaks, while the other focuses on code quality, maintainability, and structural debt. Both run async in the background on the same diff, then their findings get deduplicated and synthesized with overlapping concerns weighted higher. The workflow is pretty prescriptive about gathering context upfront and keeping the final summary tight, which matters when you're already looking at two full review passes. Useful when you want comprehensive branch audit coverage without running reviews sequentially or when a PR touches enough surface area that you'd rather parallelize the paranoia.
Install to Claude Code
npx -y skills add cursor/plugins --skill thermos --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.mdView on GitHub
Thermos
Run the two thermo review passes as async background subagents in parallel, then synthesize their results.
Workflow
- Determine the review scope from the user request, PR, current branch, or relevant changed files.
- Gather the diff and any file/context excerpts needed for reviewers to evaluate the change without guessing.
- 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.
- Pass each subagent the same scoped diff/file context and ask it to return prioritized findings with file references and evidence.
- 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.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
