Multi-Persona Code Review
eric-tramel/moraine
Coordinates a delegated review of a Moraine PR or local change by seven focused reviewer subagents, merges their findings and follows up on the fixes.
Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.
Install Multi-Model Adversarial Review
$ npx skills add cursor/plugins --skill interrogate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cursor/plugins interrogate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pstack/skills/interrogate .claude/skills/interrogate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .claude/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cursor/plugins/tree/main/pstack/skills/interrogateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cursor/plugins --skill interrogate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cursor/plugins interrogate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/pstack/skills/interrogate .agents/skills/interrogate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .agents/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cursor/plugins --skill interrogate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cursor/plugins interrogate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/pstack/skills/interrogate .cursor/skills/interrogate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .cursor/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cursor/plugins.git --path pstack/skills/interrogate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cursor/plugins --skill interrogate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cursor/plugins interrogate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/pstack/skills/interrogate .gemini/skills/interrogate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .gemini/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cursor/plugins interrogateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cursor/plugins --skill interrogate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/pstack/skills/interrogate .github/skills/interrogate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .github/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cursor/plugins --skill interrogate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cursor/plugins interrogate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/pstack/skills/interrogate .opencode/skills/interrogate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "interrogate" agent skill from https://github.com/cursor/plugins/tree/main/pstack/skills/interrogate into .opencode/skills/interrogate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interrogate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
interrogate- GitHub stars
- 10k
- Used in
- 8 other repos
- Token cost
- ~1.3k tokens
- SKILL.md length
- 674 words
- Files
- 5 (incl. references)
- Skills in repo
- 99
- Repo updated
- First seen
- Licence
- None found
At a glance
Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.
- Works in 5 steps: , Determine Scope → , State the Intent → , Spawn Reviewers → …
- Getting an adversarial second opinion on a branch before merging
- SKILL.md covers Step 1, Determine Scope, Step 2, State the Intent, Step 3, Spawn Reviewers and Step 4, Synthesize, plus 2 more sections
- Calls git
What it does
This skill sends the same code change to several differently built language models and asks each to attack it. Reviewers get an identical prompt and rubric, so the pushback comes from model diversity rather than assigned personas. The agent first works out scope from the files or diff you point to, from a full branch diff against the base branch, or from recent work, then writes one paragraph stating the intent of the change from your message, commit messages, any PR description and the code, asking you if it is unsure.
All reviewers launch together as read-only subagents, with the lineup read from an `interrogate reviewers` entry in a `pstack-models.mdc` rules file and two default reviewers used if it is missing. Fallbacks cover rejected model names without blocking the review. Each prompt is filled from `references/reviewer-prompt.md` with the intent, the diff and the rubric in `references/rubric.md`. The result is a synthesized verdict, and changes are never applied automatically. Further reference files cover code-quality review and the lead's judgment.
When your agent uses it
- Getting an adversarial second opinion on a branch before merging
- Stress testing a risky change from several independent angles
- Looking for blind spots in code written with a single model
Example prompts
- “Interrogate this branch against main and tell me where the reviewers disagree.”
- “Stress test the new caching layer and find the blind spots I missed.”
- “Tear apart the diff in src/billing before I open the PR.”
Requirements
- Access to more than one model through the host's subagent tool
- Git, for diffing against the base branch
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- , Determine Scope
- , State the Intent
- , Spawn Reviewers
- , Synthesize
- , Lead Judgment
What it can do on your machine
Read from SKILL.md and the folder at commit 9f451cf. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Multi-Model Adversarial Review loads about 1.3k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 674 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 674 words (~1,250 tokens).
“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.”
- name
- interrogate
- disable-model-invocation
- true
Files
SKILL.md and 4 other files (references) in pstack/skills/interrogate of cursor/plugins.
- SKILL.md
- references/code-quality-review.md
- references/lead-judgment.md
- references/reviewer-prompt.md
- references/rubric.md
Open the folder on GitHubat commit 9f451cf
Used in 8 other repositories
We found 8 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in cursor/plugins, which our catalogue first saw on October 7, 2026.
- chmonitor/chmonitor.claude/skills/pstack/upstream/skills/interrogate
- Sma1lboy/rove.agents/skills/pstack/skills/interrogate
- michael-denyer/pstack-claudeplugins/pstack/skills/interrogate
- backnotprop/pstackskills/interrogate
- tellahq/opensession.agents/skills/pstack-suite/skills/interrogate
- am-will/gooey-pi.agents/skills/pstack/interrogate
- jtaroreh/agystackskills/interrogate
- uzairansaruzi/p3-stackskills/interrogate
Compare with similar skills
Multi-Model Adversarial Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Multi-Model Adversarial Review this skillcursor/plugins | 10k | 8 repos | ~1.3k | Automated safety check: Pass | None | |
| Multi-Persona Code Revieweric-tramel/moraine | 117 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Adversarial Codebase Auditben-manes/caffeine | 18k | — | ~1.9k | Automated safety check: Notes | Apache-2.0 | |
| Subagent-Driven DevelopmentHoangNguyen0403/agent-skills-standard | 570 | — | ~852 | Automated safety check: Pass | MIT | |
| Clawteamwin4r/ClawTeam-OpenClaw | 1.5k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Adversarial Codebase Audit
ben-manes/caffeine
Runs a hostile review of the Caffeine Java caching library with parallel subagents that get no design docs, then challenges and consolidates their findings.
Subagent-Driven Development
HoangNguyen0403/agent-skills-standard
Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.
Clawteam
win4r/ClawTeam-OpenClaw
Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.
- Official
GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
More from cursor/plugins
All 99 skills in this repo- Official
Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
- Official
Code Design Rationale Investigator
cursor/plugins
Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.
- Official
Reflect on Session Learnings
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
- Official
Technical Writing Standard
cursor/plugins
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
- Official
Advisor Mode
cursor/plugins
Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.
- Official
Make PR Easy To Review
cursor/plugins
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.
Related
Categories
Questions about Multi-Model Adversarial Review
What does Multi-Model Adversarial Review do?
Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes. This skill sends the same code change to several differently built language models and asks each to attack it. Reviewers get an identical prompt and rubric, so the pushback comes from model diversity rather than assigned personas.
When should I use Multi-Model Adversarial Review?
Multi-Model Adversarial Review fits situations like: getting an adversarial second opinion on a branch before merging; stress testing a risky change from several independent angles; looking for blind spots in code written with a single model.
How do I install Multi-Model Adversarial Review in Claude Code?
Run `npx skills add cursor/plugins --skill interrogate -a claude-code`. Or copy the skill folder (pstack/skills/interrogate in cursor/plugins) into .claude/skills/interrogate in your project. Claude Code loads it when a task matches its description.
How do I install Multi-Model Adversarial Review in Codex?
Run `npx skills add cursor/plugins --skill interrogate -a codex`. Or copy the skill folder (pstack/skills/interrogate in cursor/plugins) into .agents/skills/interrogate in your project. Codex loads it when a task matches its description.
Can I use Multi-Model Adversarial Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cursor/plugins --skill interrogate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interrogate, .gemini/skills/interrogate, .github/skills/interrogate and .opencode/skills/interrogate in your project.
What does Multi-Model Adversarial Review need to run?
Going by SKILL.md and its folder, Multi-Model Adversarial Review needs the command-line tools its instructions call (git). Our summary lists: Access to more than one model through the host's subagent tool; Git, for diffing against the base branch.
Does Multi-Model Adversarial Review access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Multi-Model Adversarial Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Multi-Model Adversarial Review use?
No licence was found for Multi-Model Adversarial Review or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Multi-Model Adversarial Review use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4k tokens, read only when the agent opens those files.
What are the alternatives to Multi-Model Adversarial Review?
Skills that share tags, products or a category with Multi-Model Adversarial Review: Multi-Persona Code Review (eric-tramel/moraine, 117 stars), O2 Review Loop (openobserve/openobserve, 22k stars), Adversarial Codebase Audit (ben-manes/caffeine, 18k stars) and Subagent-Driven Development (HoangNguyen0403/agent-skills-standard, 570 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Multi-Model Adversarial Review?
cursor (a GitHub organization, an official publisher) maintains it in cursor/plugins, which has 10,130 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 6, 2026.
Source: cursor/plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.