interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
Skill by fitchmultz
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.
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/fitchmultz-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.
About
Use cases: testing, ml
Reviews
Write a reviewNo 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. Checked Oct 25, 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
- Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
- License
- MIT
- Instructions
- 72 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- code-quality-review.md · references/
- lead-judgment.md · references/
- reviewer-prompt.md · references/
- rubric.md · references/
SKILL.md (first lines)
# Interrogate Read [the Pi execution contract](../../docs/harness/pi.md) and select the authorized delegated or inline route. Recheck before delegation. Report self-performed work and any loss of independence, isolation, model diversity, or parallelism. Adversaries try to break a change or a design. A finding survives only when a run proves it. Report the findings. Do not apply fixes. ## Frame The scope is what the user names. Otherwise it is the branch diff from its merge base with the base branch, through the working tree. State the intent with the **in-your-own-words** skill, from the user's message, the commits, and the PR description. Ask the user when the intent is unclear. ## Attack passes Run Phase A steps 3 and 4 and Phase B of the **arena** skill with distinct adversarial lenses. Use configured `interrogate reviewers` choices when available. Give each authorized reviewer an isolated copy of the scope, including uncommitted changes, and this brief. Without a provider, run the same attack passes serially yourself; keep their repros separate and label the review self-performed. > Break this change. Prove each finding with a run against the real code, such as a failing test, a repro script, or command output that shows the wrong behavior. For a design or plan, run a prototype or probe the current tree. Keep repros in your own worktree. Report each finding with a title, the exact command, the output it printed, and the output the intent requires. Leave out anything you did not run. That covers style, naming, structure, and risks that need a future change to matter. No findings is a valid result. ## Verify Verify each finding per arena Phase F by rerunning its command. Keep a finding when the output shows the failure and the failure breaks the intent. Drop the rest. Merge findings that share a root cause. Skip arena Phases C, D, and E. Attack passes find different failures, so the verdict keeps every verified finding, not one reviewer's list. ## Output - **Intent**: the restatement. - **Findings**: for each verified finding, the command, its output, how it breaks the intent, and the review lens that found it. Say "no verified findings" when none survive. - **Dropped**: for each lens, the count of dropped findings and why. State whether the passes were independent or self-performed.
From fitchmultz/pi-pstack, MIT.
More from fitchmultz/pi-pstack
- 0.541score
poteto-mode
fitchmultz
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: AClaude Code +9 - 0.541score
architect
fitchmultz
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.541score
create-verification-skill
fitchmultz
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.541score
how
fitchmultz
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.536score
arena
fitchmultz
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: AClaude Code +9 - 0.536score
automate-me
fitchmultz
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: AClaude Code +9 - 0.536score
maintain-verification-skill
fitchmultz
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillAFreshness: AClaude Code +9 - 0.533score
no-comments
fitchmultz
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 20, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fitchmultz/pi-pstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fitchmultz
- 0.541score
poteto-mode
fitchmultz
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: AClaude Code +9 - 0.541score
architect
fitchmultz
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.541score
create-verification-skill
fitchmultz
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.541score
how
fitchmultz
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.536score
arena
fitchmultz
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: AClaude Code +9 - 0.536score
automate-me
fitchmultz
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: AClaude Code +9
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.
Cite this page
interrogate skill. Agent Mart. https://agentmart.dev/skills/fitchmultz-interrogate (last updated 2026-10-24)