Skip to content
Agentmart
Submit a tool

interrogate

Adversarial review of a change by one child per configured reviewer.

Skill by kevherro

IndexedMIT
Write a review

Chalk Labs

Need help deploying interrogate?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kevherro-interrogate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Adversarial review of a change by one child per configured reviewer. Use for /interrogate, "tear this apart", or "multi-model review".

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/interrogate

What's inside

Skill name
interrogate
Description
Adversarial review of a change by one child per configured reviewer. Use for /interrogate, "tear this apart", or "multi-model review".
License
MIT
Instructions
50 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/models.md, references/harness.md

Files (3)

  • SKILL.md
  • reviewer-brief.md · references/
  • rubric.md · references/

SKILL.md (first lines)

# Interrogate

Stress a change with independent read-only reviewers. The parent
judges. Do not auto-apply.

The `reviewers` list in the discovered **mestack** skill's
`references/models.md` is the panel. Empty list: the parent reviews
once, labeled `parent`.
A slug this session cannot run uses its declared fallback, else it is
a dropout. Do not substitute an undeclared model.

## Steps

1. Scope. User-named files or diff if given. Else
   `git diff <base>...HEAD` including the working tree. Base is
   `main` unless the repo says otherwise.
2. Intent. One paragraph: what this change is for. User message,
   commits, PR body, then the diff. Reviewers challenge fit to
   intent, not the intent itself. If intent is unclear, ask.
3. Spawn. Parent launches one read-only child per remaining reviewer
   in one turn, per the **mestack** skill's `references/harness.md`.
   Read-only reviewers may share a checkout; they must not write.
   Same brief for every child: intent, scope, and
   [references/rubric.md](references/rubric.md). Fill
   [references/reviewer-brief.md](references/reviewer-brief.md).
4. Parent reads the diff again. Child summaries are untrusted.
5. Judge. You have the goal and the constraints. Bucket every
   finding:
   - **Act on.** Would block a real merge.
   - **Consider.** Real, cost unclear.
   - **Noted.** Valid, not actionable now.
   - **Dismissed.** Wrong, nit, or missing context. Say why.
   Consensus (2+ children, same issue) is high-confidence. A lone
   finding still appears, with its model.

**Reply:**

### Intent
> the paragraph from step 2

### Reviewers
one bullet each: label, slug or `parent`, finding count, dropouts

### Act on / Consider / Noted / Dismissed
each finding: what, evidence, who raised it, why this bucket

### Agreement
where they agreed, where they split

From kevherro/mestack, MIT.

More from kevherro/mestack

Signals

Stars
0
Forks
2
Open issues
0
Last commit (this folder)
Oct 23, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kevherro

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get interrogate running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying interrogate?

CallGet help
Cite this page

interrogate skill. Agent Mart. https://agentmart.dev/skills/kevherro-interrogate (last updated 2026-10-24)