Explicit-only interview loop for stress-testing a plan, decision, or idea. Use only when the user asks to grill, interrogate, interview, or stress-test their thinking before action.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask at most three independent, high-value frontier questions about material unresolved decisions in one round. Prefer a usable structured-question tool when available; otherwise ask concise numbered questions. Give your recommended answer. Then wait for the user's answers before the next round.
Format a round like so:
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
Word each question so "yes" accepts your recommended answer.
Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Finding facts is your job, never the user's. Discover repository and environment facts before asking questions, using available tools directly. The decisions are the user's: put each to them and wait.
The session is done when no material unresolved decision remains. Respect choices already settled by the user or authoritative evidence; do not exhaust speculative branches. End by reporting the shared understanding and open decisions. Do not implement automatically; implementation requires a separate user request.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Read public X/Twitter post URLs as structured evidence through the ADHX API. Use for relevant user-provided or research-discovered x.com, twitter.com, or adhx.com links. ADHX does not search X, and long-form Article content may be incomplete.
The English summary is being prepared. Showing the original description.
Design, review, or report a measured performance comparison. Use for benchmark methodology, speedup or regression claims, and performance-based choices; not generic performance discussion, ordinary dependency bumps, local renames, or prose edits.
The English summary is being prepared. Showing the original description.
Trace what an actual code change could break beyond its diff when interfaces, serialized data, database schemas, configuration, caches, lifecycle ordering, or cross-language consumers are involved. Use for explicit impact analysis; not local renames, prose edits, ordinary dependency bumps, or generic architecture discussion.
The English summary is being prepared. Showing the original description.
Shared vocabulary for designing deep modules, interfaces, seams, adapters, leverage, and locality. Use when designing or reshaping module boundaries, making code more testable, or evaluating interface depth.
The English summary is being prepared. Showing the original description.
Plan or implement retirement of a system, API, feature, persisted configuration, or database shape. Use for compatibility cutovers, explicit deprecation review, or an explicit unreleased replacement decision, including determining whether consumers or data exist; not ordinary dependency bumps, local renames, prose edits, or generic architecture discussion.
The English summary is being prepared. Showing the original description.
Disciplined diagnosis loop for hard bugs, regressions, flaky failures, and performance problems with unclear cause. Use for root-cause debugging after a concrete symptom exists; do not use for routine implementation or speculative cleanup.
The English summary is being prepared. Showing the original description.