interrogate
Skill7 starsChanged 34 days agoMITView on GitHub
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.
80 other projects use a version of this, 38 of them edited.
Adopted by
Most recently taken up by
- shiwenbin1617/pstacktheir own version, first seen Nov 16, 2026
- backnotprop/pstacktheir own version, first seen Nov 15, 2026
- B16B1RD/bb-writtheir own version, first seen Nov 15, 2026
- sammyjoyce/prime-pstackedited, first seen Nov 15, 2026
- pronvis/skillsedited, first seen Nov 15, 2026
- upamune/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use ketchup-video, make-bot-ui and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 14 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 20 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
TheOnlyFusionCubeSkillstatechart
Draw what an app's user sees as a Mermaid statechart from a TLA+ model. States are gray if they work, red if still wrong, and green if fixed. Each bug TLC finds is a numbered path. Use for /statechart, \"show the PM the bug\", or to turn an agreed chart into a TLA+ skeleton.
Also in 16 projects that use this
Other versions80 projects use a version of this.
Word for word · 0
None found.
Edited · 38
- moeru-ai/xsai★ 66733% same
- uzairansaruzi/p3-stack★ 12675% same
- dsebban/skills★ 7126% same
- overextended/skills★ 2227% same
- caidanw/skills★ 1144% same
- kkgogogo17/pi-pstack★ 979% same
- stainless-code/lossless★ 416% same
- bnema/pi-pstack★ 285% same
- dhanji4U/skills★ 265% same
- EvanBatten/pstack-for-cc★ 258% same
28 more not listed
Wrote their own version · 42
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- backnotprop/pstack★ 4.2ksame name
- savannahfeder/agentbox★ 419same name
- jtaroreh/agystack★ 128same name
- painhardcore/pstack★ 22same name
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- creedants/pstack-t3★ 18same name
- korallis/skills-collection★ 14same name
- mariusflorescu/pstack-t3★ 13same name
32 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository53 other files it gives its agents.
- architectSkill
- arenaSkill
- automate-meSkill
- benchmark-checklistSkill
- blast-radiusSkill
- broSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- figure-it-outSkill
- howSkill
- in-your-own-wordsSkill
- ketchupSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- no-commentsSkill
- poteto-modeSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-build-the-leverSkill
- principle-encode-lessons-in-structureSkill
- principle-exhaust-the-design-spaceSkill
- principle-experience-firstSkill
- principle-explain-the-numberSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-guard-the-context-windowSkill
- principle-laziness-protocolSkill
- principle-make-operations-idempotentSkill
- principle-migrate-callers-then-delete-legacy-apisSkill
- principle-minimize-reader-loadSkill
- principle-model-the-domainSkill
- principle-never-block-on-the-humanSkill
- principle-outcome-oriented-executionSkill
- principle-prove-it-worksSkill
- principle-redesign-from-first-principlesSkill
- principle-separate-before-serializing-shared-stateSkill
- principle-sequence-verifiable-unitsSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- principle-type-system-disciplineSkill
- recallSkill
- reflectSkill
- setup-pstackSkill
- sharpenSkill
- show-me-your-workSkill
- swarmSkill
- tddSkill
- teachSkill
- technical-writingSkill
- typescript-best-practicesSkill
- unslopSkill
- whySkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 79 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
If the user points at specific files or a diff, use that
- Distinctive: line 18
If on a feature branch, run git diff main...HEAD (or the appropriate base branch) for the full changeset
- Distinctive: line 19
If the user's message references recent work, gather the relevant files
- Distinctive: line 25
Before spawning reviewers, state the intent explicitly.
- Distinctive: line 32
Write one clear paragraph.
- Very specific: line 45
If pstack_task reports an unavailable configured model, run /setup-pstack before retrying.
- Very specific: line 47
Read references/reviewer-prompt.md and fill in the template with:
- Distinctive: line 65
Note disagreements: If one model flags something and another explicitly says the opposite, that's useful context for the verdict.
- Very specific: line 71
Read references/lead-judgment.md for the full framework.
“Common” is measured: kept by at least 6 in 10 of the 79 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Interrogate
Spawn one reviewer per configured model to adversarially review code changes. Each model gets the same prompt and rubric. The adversarial signal comes from model diversity, not assigned personas. Models differ in blind spots, priors, and reasoning patterns. Agreement across models is high-confidence signal; lone-model findings are worth reading but lower confidence.
The deliverable is a synthesized verdict. Do NOT auto-apply changes.
Step 1, Determine 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) plus any surrounding context files the reviewers need to understand the code.
Step 2, State the Intent
Before spawning reviewers, state the intent explicitly. What is this code trying to accomplish? Derive this from:
- The user's message
- Commit messages
- PR description if one exists
- The code itself
Write one clear paragraph. Reviewers challenge whether the work achieves the intent well, not whether the intent itself is correct. If you're unsure about the intent, ask the user before proceeding.
Step 3, Spawn Reviewers
Launch all reviewers in one parallel pstack_task call. Read the interrogate-reviewers list from ~/.pi/agent/pstack-models.json and create one task per entry. Extend or shrink the Reviewer A/B/C/D labels to match. Without a config, run two reviewers. pstack_task resolves the available upstream pair and falls back to the parent for an unavailable family.
Pass role: "interrogate-reviewers" on each task entry. The extension cycles the configured list, one model per reviewer.
For each reviewer:
agent:general-purposerole:interrogate-reviewersreadonly:true
If pstack_task reports an unavailable configured model, run /setup-pstack before retrying. Do not substitute an unverified slug. inherit-parent is a valid assignment, not a model slug.
Read references/reviewer-prompt.md and fill in the template with:
- The stated intent
- The diff or file contents
- The review rubric from
references/rubric.md - The code-quality lens from
references/code-quality-review.md
The same filled template goes to all reviewers, so every model applies the code-quality lens.
Each reviewer produces structured findings as described in the prompt template.
Step 4, Synthesize
As results come back, build a unified picture:
- Parse all findings from the reviewers
- Identify consensus. Findings raised by 2+ models independently are highest signal.
- Identify lone-model findings. Still worth reading, but weight accordingly.
- Deduplicate. Different models may describe the same issue differently. Merge these and note which models raised it.
- Note disagreements. If one model flags something and another explicitly says the opposite, that's useful 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. Reviewers only see a slice of the codebase. You have the full context (the goal, the constraints, the timeline, which tradeoffs were already considered). Use that context aggressively.
Categorize every finding using these buckets:
- Act on. Real issues affecting correctness, security, or maintainability given the actual goals. These would block a real PR.
- Consider. Legitimate points, but you're not sure they outweigh the cost of addressing them right now. Worth the user's attention.
- Noted. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact given the current stage.
- Dismissed. Wrong, nitpicky, or missing context. Brief explanation why.
For each finding, include:
- Which model(s) raised it
- The category (act on / consider / noted / dismissed)
- A one-line rationale for the categorization
Output Format
Present the verdict in this structure:
Intent
[The stated intent paragraph from Step 2]
Reviewers
- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)
Act On
[Findings that should be addressed. For each: description, which models raised it, why it matters.]
Consider
[Findings worth thinking about. For each: description, which models raised it, tradeoff involved.]
Noted
[Valid but low-priority. Brief list.]
Dismissed
[Rejected findings with brief rationale. This shows the user what was filtered out and why, so they can override your judgment if they disagree.]
Agreement Map
[Where did models agree, where did they diverge, and what does the pattern of agreement/disagreement tell us?]
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

