interrogate
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 许可
- MIT
- 最近更新
- 2026-10-28
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- 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.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/code-quality-review.md5.1 KB
- 参考文档references/lead-judgment.md2.2 KB
- 参考文档references/reviewer-prompt.md2.2 KB
- 参考文档references/rubric.md4.7 KB
03 SKILL.md 正文
Interrogate
Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. The deliverable is a synthesized verdict. Do NOT auto-apply changes.
Step 1, 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 with any surrounding context files the reviewers need to understand the code.
Step 2, Intent
Before spawning reviewers, state the intent in one clear paragraph from the user's message, commit messages, the PR description if one exists, and the code. If you're unsure about the intent, ask the user before proceeding.
Step 3, Spawn Reviewers
Launch all reviewers in a single message, one delegate_task call per entry on the interrogate reviewers line in .agents/pstack-models.md in the project's main checkout ("$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")/.agents/pstack-models.md", which may not exist), labeled Reviewer A, B, and so on to match the entry count. If that line is missing, use the table defaults, one reviewer per entry.
| Subagent | Default model |
|---|---|
| Reviewer A, B, ... in order | claudeAgent/claude-opus-5-5 high, codex/gpt-6.1-sol xhigh |
Each reviewer gets no isolation, a brief that says "Do not edit, create, commit, or push files.", and target set from its configured entry, or its table default when there is no configured line. You run git status afterward. A role line is <role>: <entry>, <entry>, ..., and a panel role runs one subagent per entry. An entry <provider>/<model> <effort> becomes target: {providerInstanceId: <provider>, model: <model>, options: {effort: <effort>}}, with reasoningEffort instead of effort for codex. inherit-parent means omit target. The effort is a ceiling: lower it for routine work, never raise it, and never set fastMode.
Read references/reviewer-prompt.md and fill in the same template for every reviewer with the stated intent, the diff or file contents, the rubric from references/rubric.md, and the code-quality lens from references/code-quality-review.md. Set each subagent's effort for the job, lowering its line's effort for routine work and never raising it. See the Subagents section of the poteto-mode skill.
Step 4, Synthesize
As results come back, build a unified picture. Parse every reviewer's findings. Merge findings that describe the same issue differently, and note which models raised each one. Findings two or more models raised independently are the highest signal. Read a lone model's finding, but weight it accordingly. Note disagreements. If one model flags something and another explicitly says the opposite, that is 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. Put every finding in one of four buckets, with the model(s) that raised it and a one-line rationale.
- Act on. Real issues affecting correctness, security, or maintainability given the actual goals. They would block a real PR.
- Consider. Legitimate, but you're not sure they outweigh the cost of addressing them now. Worth the user's attention.
- Noted. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact at this stage.
- Dismissed. Wrong, nitpicky, or missing context, with a brief reason.
Output Format
Intent
[The stated intent paragraph from Step 2]
Reviewers
- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)
Act On
[Each: description, which models raised it, why it matters.]
Consider
[Each: description, which models raised it, the tradeoff.]
Noted
[Brief list.]
Dismissed
[Each with a brief rationale.]
Agreement Map
[Where models agreed and diverged, and what that pattern tells us.]
04 同仓库更多 Skills
patchbook-update
Pull upstreams into a repo that keeps its changes in a patchbook (.patchbook/), repair what broke from each change's intent, test and review, then merge and deploy only when the sync was clean or the test command passes, and otherwise ask, opening a pull request when there are commits to push. Use when a scheduled task or the user says to update a patchbook repo, or for /patchbook-update or $patchbook-update.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
verify-patchbook
Drive the patchbook CLI from this checkout in a disposable sandbox (its own git repos, store, config and a fake model) and capture a transcript as proof. Use to reproduce a patchbook bug, run an issue's repro script, or prove a change to clone, init, record, the pre-commit hook, build, status, check, sync or upstream works the way a user would see it.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or $technical-writing, or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.