interrogate
/interrogate
Uruchamia adwersaryjny przegląd kodu lub różnic przez niezależnych recenzentów i zbiera wspólne ustalenia.
Ocena i bezpieczeństwo
- Pliki w paczce
- 6
- Skrypty
- 0
- Komentarze HTML
- 1
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 24.08.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.
Co robi i kiedy
Uruchamia adwersaryjny przegląd kodu lub różnic przez niezależnych recenzentów i zbiera wspólne ustalenia.
Oryginalny opis (EN)
Run an adversarial review of code or a diff through independent reviewers, then lead-judge consensus, disagreements, and false positives. Use when the user asks to interrogate, challenge, stress-test, find blind spots, perform multi-model review, or when `henry-mode` needs adversarial judgment of a risky change.
Jak działa
- Availability and fallback
- 1. Determine scope
- 2. State intent
- 3. Launch independent reviewers
- 4. Aggregate
- 5. Lead judgment
- Output contract
Podgląd SKILL.md
--- name: interrogate description: Run an adversarial review of code or a diff through independent reviewers, then lead-judge consensus, disagreements, and false positives. Use when the user asks to interrogate, challenge, stress-test, find blind spots, perform multi-model review, or when `henry-mode` needs adversarial judgment of a risky change. --- # Interrogate Give independent reviewers the same intent, code, and rubric. Diversity comes from independent reasoning and, where genuinely available, different model families—not invented personas or model aliases. The deliverable is a lead-reviewed verdict; never auto-apply findings. ## Availability and fallback | Harness | Parallel mechanism | Model selection | Fallback | |---|---|---|---| | Cursor | Available Task/subagent calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes | | Claude Code | Available Agent/Task calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes | | Codex / T3 | `spawn_agent`, drained with `wait_agent` | Valid overrides only when offered | Run waves within slot limits; inherit the parent model | | No delegation | None | None | Apply the rubric through separate sequential passes and label the result self-reviewed | Only delegate when current user and system policy permit it. If true model diversity is unavailable, disclose that; never pretend reviewer labels are different models. ## 1. Determine scope Use the exact files or diff the user names. Otherwise inspect the full feature-branch diff against its appropriate merge base. Include only surrounding files needed to trace the changed behavior; give every reviewer the same package. ## 2. State intent Write one paragraph describing what the change is meant to accomplish, derived from the user's request, commit/PR context, and code. Ask only if ambiguity would materially change the review. Reviewers challenge execution, not the chosen product goal. ## 3. Launch independent reviewers Read and fill these references: - [`references/reviewer-prompt.md`](references/reviewer-prompt.md) - [`references/rubric.md`](references/rubric.md) - [`references/code-quality-review.md`](references/code-quality-review.md) Launch as many reviewers as the user requested or the harness can support usefully; default to three independent passes. Each reviewer is read-only and receives the identical filled prompt. Use model overrides only from valid harness-advertised choices. Require structured findings with severity, location, evidence, and an optional concrete suggestion. ## 4. Aggregate Drain every reviewer. Merge duplicate findings, identify independent agreement, retain lone findings at lower confidence, and surface explicit disagreement. Inspect relevant code yourself before accepting a claim. ## 5. Lead judgment Read [`references/lead-judgment.md`](references/lead-judgment.md), then categorize every finding: - **Act on:** concrete correctness, security, or maintainability issues that should block the change. - **Consider:** legitimate tradeoffs whose benefit may not exceed their cost now. - **Noted:** valid but low-priority or context-dependent observations. - **Dismissed:** wrong, nitpicky, hypothetical, or missing known context. Name the reviewers that raised each finding and give a one-line rationale. Consensus is strong evidence, not a substitute for tracing the code. ## Output contract 1. `Intent` 2. `Reviewers`—configuration, model-diversity status, and finding count 3. `Act On` 4. `Consider` 5. `Noted` 6. `Dismissed` 7. `Agreement Map` 8. `Coverage Gaps` Do not edit code or create review comments unless the user separately authorizes those actions. <!-- Adapted from poteto/pstack interrogate, MIT License, Lauren Tan, cursor/plugins@51a96e0. -->
Pliki w paczce (6)
- LICENSE 1 KB
- SKILL.md 4 KB
- references/code-quality-review.md 5 KB
- references/lead-judgment.md 3 KB
- references/reviewer-prompt.md 3 KB
- references/rubric.md 5 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · caezium/skills | 90 | MIT |
| hootener/brain | 100 | MIT |
| requie/endostack | 100 | MIT |
| Sup-Film/pstack-omp-lean | 100 | MIT |
| RIJUDEVx/agent-skills | 90 | MIT |
| chmonitor/chmonitor | 90 | GPL-3.0 |
| richardochristjia/skills | 90 | MIT |
| chhoumann/t3-pstack | 90 | MIT |
| backnotprop/pstack | 90 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 0137cc5af695 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100comms-interrogate
Krytykuje diff równolegle z wielu perspektyw w trybie tylko do odczytu i składa uwagi recenzentów w jeden werdykt. - 90mroowa-interrogate
Przegląda zmiany w kodzie w sposób adwersarialny jednym czytelnikiem bez prawa zapisu i wnioskiem rodzica, szukając ślepych punktów. - 100lie-detector
Przeprowadza wielomodelowy przegląd adwersarialny zmian i spornych projektów przed wydaniem: kilku recenzentów na różnych modelach kwestionuje zmianę niezależnie, aby wykryć ślepe punkty i twierdzenia bez pokrycia.