interrogate

Files (5)

• SKILL.md
• code-quality-review.md · references/
• lead-judgment.md · references/
• reviewer-prompt.md · references/
• rubric.md · references/

SKILL.md (first lines)

> Hermes port. Before any spawn, model pick, question, or transcript read, load `pstack:hermes-runtime` and obey it. That contract overrides Cursor Task, subagent_type, AskQuestion, ~/.cursor paths, cloud agents, and cursor-team-kit. poteto-agent is a skill, not a profile. Invoke siblings as `pstack:<name>`.

# Interrogate

Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. The deliverable is a synthesized verdict. Do NOT auto-apply changes.

## Step 1, Scope

Identify what to review from context:

- If the user points at specific files or a diff, use that.
- If on a feature branch, run `git diff main...HEAD` (or the appropriate base branch) for the full changeset.
- If the user's message references recent work, gather the relevant files.

Package the diff or file contents with any surrounding context files the reviewers need to understand the code.

## Step 2, Intent

Before spawning reviewers, state the intent in one clear paragraph from the user's message, commit messages, the PR description if one exists, and the code. If you're unsure about the intent, ask the user before proceeding.

## Step 3, Spawn Reviewers

Launch one reviewer per entry on the `interrogate reviewers` line in `$HERMES_HOME/pstack/models.md`, labeled Reviewer A, B, and so on. Missing line means one reviewer on `inherit-parent`. Do not duplicate `inherit-parent` to fake a second model. Say so in the report.

Each reviewer is read-only. The brief forbids edits. Spawn per `pstack:hermes-runtime`. Same-model seats go in one `delegate_task` call. A confirmed different slug is its own `hermes chat -q` process.

Read `references/reviewer-prompt.md` and fill in the same template for every reviewer with the stated intent, the diff or file contents, the rubric from `references/rubric.md`, and the code-quality lens from `references/code-quality-review.md`.

## Step 4, Synthesize

As results come back, build a unified picture. Parse every reviewer's findings. Merge findings that describe the same issue differently, and note which models raised each one. Findings two or more models raised independently are the highest signal. Read a lone model's finding, but weight it accordingly. Note disagreements. If one model flags something and another explicitly says the opposite, that is context for the verdict.

## Step 5, Lead Judgment

You are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator. Read `references/lead-judgment.md` for the full framework. Put every finding in one of four buckets, with the model(s) that raised it and a one-line rationale.

- **Act on**. Real issues affecting correctness, security, or maintainability given the actual goals. They would block a real PR.
- **Consider**. Legitimate, but you're not sure they outweigh the cost of addressing them now. Worth the user's attention.
- **Noted**. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact at this stage.
- **Dismissed**. Wrong, nitpicky, or missing context, with a brief reason.

## Output Format

### Intent
> [The stated intent paragraph from Step 2]

### Reviewers
- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)

### Act On
[Each: description, which models raised it, why it matters.]

### Consider
[Each: description, which models raised it, the tradeoff.]

### Noted
[Brief list.]

### Dismissed
[Each with a brief rationale.]

### Agreement Map
[Where models agreed and diverged, and what that pattern tells us.]

From klgraham/pstack-hermes, MIT.

More from klgraham/pstack-hermes