Thermos

---
name: thermos
description: "Use for combined correctness and code-quality reviews."
license: MIT
metadata:
  author: jstack-maintainers
  source: michael-denyer/pstack-claude
  source-version: "0.9.130"
  source-commit: d88063f3355a5ecff0e6dbb890a11bab4b08bc2e
  owner: software-factory
  risk: low
  capabilities: jstack,engineering-workflow
---

# Thermos

On Codex, Cursor, or another non-Claude runtime, read the [runtime mapping](../poteto-mode/references/harness-tools.md), including its per-skill notes, before following this skill.

On GitHub Copilot, read the [platform mapping](../poteto-mode/references/copilot-tools.md), including its per-skill notes, before following this skill.

On Muse, read the [platform mapping](../poteto-mode/references/muse-tools.md), including its per-skill notes, before following this skill.

On Antigravity, read the [platform mapping](../poteto-mode/references/agy-tools.md), including its per-skill notes, before following this skill.

Run the two thermo review passes with authorized native workers, then synthesize their results. For a Claude plugin, use the namespaced companion agents below; for a direct install, use their bare names under `.claude/agents/`. On other runtimes, use the runtime mapping and read their bundled definitions under `../poteto-mode/references/agents/`. If delegation is unavailable or not authorized, perform both passes sequentially and report that limitation.

## 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: "software-factory-skills:thermo-nuclear-review-subagent"` for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.
   - `subagent_type: "software-factory-skills:thermo-nuclear-code-quality-review-subagent"` for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.

   Set `model` on both to the `thermos reviewers` line in `jstack-models.md`, or to the default in [Models](#models) if the sheet or that line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the `Agent` tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. Pick each subagent's reasoning level for the job, per the Subagents section of the **poteto-mode** skill.
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.

## Models

Role defaults originate from the upstream `plugins/pstack/models.json`. Refresh them through `scripts/vendor_jstack.py` after reviewing the upstream change. A matching role line in the `jstack-models.md` override sheet overrides each at runtime; `/setup-jstack` writes it and lists its path per runtime.

- thermos reviewers: `opus`

## Reasoning effort

A role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. On Claude Code, `session` sets no effort. On other runtimes, follow the platform mapping for `session`. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. Pass the level as the dispatch's effort field and keep the `subagent_type` you would otherwise use. That is `effort` on the Claude Code `Agent` call and `reasoning_effort` on Codex's `spawn_agent`. On Muse it is `effort` on a Workflow child; a `subagent_spawn` dispatch keeps the session's effort.