Five Roman magistrate evaluation frameworks for multi-perspective project assessment. Invoke individually (/censor, /tribune, /praetor, /augur, /legatus) or convene the full Senate (/council).
Use when user says "augur", "/augur", "augurs reading", "strategic review", "market review", "risk assessment", "viability check", or requests an evaluation focused on market timing, strategic positioning, competitive landscape, or business viability. Triggers on requests to evaluate "should we build this", "is the timing right", "who are our competitors", "what's our market", or any request for a strategic-level assessment of whether the venture should exist at all. Also triggers when a user wants a Cicero-style or strategic critique focused on omens, timing, and the political landscape. Always use this skill when the user invokes any variation of "augur", "cicero", or "reading" in the context of evaluating work.
Use when user says "censor", "decree", "/censor", "/decree", "censors decree", or requests a harsh Roman-style evaluation of a project, idea, business, or codebase. Triggers on requests for austere critical review, "judge this", "what's wrong with this", or honest assessment of any project at any stage. Also triggers when a user wants a Cato-style or Roman-themed critique. Always use this skill when the user invokes any variation of "Cato", "censor", or "decree" in the context of evaluating work.
Use when user says "council", "rome", "/council", "/senate", "council of rome", or requests a comprehensive multi-perspective evaluation of a project, idea, business, or codebase using the Roman magistrate framework. Also triggers when the user wants to invoke multiple Roman reviewers simultaneously, or asks for a "full Roman review", "senate review", or "convene the council". Routes to individual magistrate skills or dispatches multiple magistrates in parallel. This is the orchestration layer for the full Council of Rome evaluation suite.
Use when user says "legatus", "/legatus", "legatus campaign", "ops review", "devops review", "deployment review", "infrastructure review", "operations review", or requests an evaluation focused on operational readiness, deployment, infrastructure, monitoring, incident response, team capacity, or production reliability. Triggers on requests to evaluate "can we deploy this", "is this production ready", "what happens when it goes down", "review our infrastructure", or any request for an operations and logistics focused evaluation. Also triggers when a user wants a Pompey-style or military logistics critique. Always use this skill when the user invokes any variation of "legatus", "pompey", or "campaign" in the context of evaluating work.
Use when user says "praetor", "/praetor", "praetors inquisition", "security review", "compliance review", "legal review", "audit", or requests an evaluation focused on security, legal exposure, data privacy, regulatory compliance, or contractual obligations. Triggers on requests to evaluate vulnerabilities, "is this secure", "what's our legal exposure", "audit this", "check compliance", or any request for a security-first or compliance-focused evaluation. Also triggers when a user wants a Sulla-style or law-focused critique. Always use this skill when the user invokes any variation of "praetor", "sulla", or "inquisition" in the context of evaluating work.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Five Roman magistrates walk into your codebase.
A suite of opinionated AI evaluation skills that deploy five Roman magistrates to assess projects across architecture, UX, security, strategy, and operations. No compliment sandwiches. No Greek flattery. Just the standard of the Republic.
| Magistrate | Command | Historical Figure | Domain |
|---|---|---|---|
| The Censor | /censor | Cato the Elder | Code quality, architecture, structural integrity, technical debt |
| The Tribune | /tribune | Gaius Gracchus | UX, accessibility, user advocacy, equity, the people's voice |
| The Praetor | /praetor | Lucius Cornelius Sulla | Security, compliance, legal exposure, data privacy, dependencies |
| The Augur | /augur | Marcus Tullius Cicero | Market timing, competitive landscape, strategic risk, viability |
| The Legatus | /legatus | Pompey the Great | DevOps, deployment, monitoring, disaster recovery, operations |
The Senate (/council) convenes all five simultaneously and surfaces where they disagree — because that's where the most valuable strategic tensions live.
# Add the marketplace
/plugin marketplace add therealatreides/council-of-rome
# Install the plugin
/plugin install council-of-rome@council-of-rome
Clone this repo and copy the skill folders into your Claude Code skills directory:
git clone https://github.com/therealatreides/council-of-rome.git
cp -r council-of-rome/plugins/council-of-rome/skills/* ~/.claude/skills/
skills/censors-decree/)Each skill is a standalone SKILL.md file. Copy it into your agent's skills directory — the format follows the open Agent Skills specification.
Invoke any magistrate individually:
/censor # Structural integrity review (Cato)
/tribune # User advocacy review (Gracchus)
/praetor # Security & compliance review (Sulla)
/augur # Strategic risk assessment (Cicero)
/legatus # Operations & deployment review (Pompey)
Or convene the full Senate:
/council # All five magistrates + Senate hearing
/council --magistrates=censor,augur # Select specific magistrates
Each magistrate produces a structured report with Latin severity classifications, findings organized by Vice → Erosion → Decree, and a final verdict.
Each magistrate has:
The Council layer adds a Senate Hearing that identifies contradictions between magistrates — speed vs. safety, user desire vs. structural integrity, market timing vs. readiness — and surfaces these tensions as the most actionable output.
| Magistrate | Unique Feature |
|---|---|
| Augur | Core Assumptions Register — identifies what must be true for the venture to succeed, then tests each assumption. Includes a mandatory Kill Question. |
| Legatus | Three Mandatory Scenarios — 3AM incident response, key person departure, and 10x scale stress test. |
| Tribune | Explicitly identifies who is served and who is abandoned — the section "who is abandoned" must never be empty. |
| Praetor | Dependency Dossier — treats every third-party library as a potential collaborator with the enemy. |
| Council | Senate Hearing — surfaces where magistrates contradict each other, which is where real strategic tradeoffs live. |
npx claudepluginhub therealatreides/council-of-rome --plugin council-of-romeMulti-perspective council analysis. Spawns parallel cognitive perspectives to analyze questions, plans, and ideas from multiple angles with structured dialectical synthesis.
Adversarial plan review using red-team/blue-team agents -- generates what-if questions and grounds answers in plan artifacts with configurable tool scope
Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a judge delivers a structured verdict with epistemic labels. Bundles plan-review-integrator for applying review findings back into implementation plans.
ES: Vuelve a Claude en tu contra para criticar a fondo una idea, un plan o un proyecto entero — sin validar ni suavizar — por ocho ángulos, con investigación de fracasos reales y un veredicto priorizado de qué arreglar. EN: Turn Claude against you to harshly critique an idea, plan, or whole project across eight angles with a prioritized verdict.
Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log.
Truth-seeking sparring partner for Claude Code. Challenges claims, decisions, and documents through structured dialectical analysis.