English · Русский

Consilium Principis

Several perspectives. One decision. Quotes checked against the source.

An AI advisory board for Claude Code and MCP hosts. Ask about a difficult choice: advisors examine it through different lenses, challenge one another and give you one next step. A line marked 🔵 is checked by code against the source text word for word. If the line is absent, the advisor does not present it as a quote.

Example: “What would Marcus Aurelius say about this?” Consilium can label a model's interpretation 🟡, show a source-checked passage 🔵, or decline to quote when the corpus does not support one. Watch the live refusal and verification →

Quick start in Claude Code

/plugin marketplace add ilyautov/consilium-principis
/plugin install consilium-principis@consilium-marketplace

Then ask: “Help me decide what to focus on.” For Claude Desktop, other MCP hosts and local setup, see Installation. The plugin uses your existing agent; model/provider charges, if any, follow your host setup.

Explore: See a session · How quote verification works · Installation · Limits

What this is

Consilium Principis is a skill and MCP server for AI agents. You connect it to your agent, ask a question you need to decide on, and it gathers a board around the table: Sun Tzu, Marcus Aurelius, Machiavelli, Epictetus, and whoever else you add. Each looks at it through their own lens, leans on their own texts, and argues — with you and with the others. At the end you get one synthesis and one next step. And if the question is quantifiable ("which is more worthwhile, X or Y"), the board doesn't eyeball it — it breaks the decision into numbers and runs them through a Monte Carlo.

This project doesn't ask an AI to roleplay a sage — we tried to build a tool, not a roleplay game or an aphorism generator. Why you can trust its quotes comes next.

One honest thing about who's at the table: these aren't the thinkers themselves but their AI versions — a prism of their views over the corpus of their public texts. Nobody is "speaking from beyond the grave." An advisor holds the author's lens and leans on their words, but it stays a model — and we say so plainly.

Consilium needs no separate API key. It runs on the agent you already have, whose model or provider may have its own charges. Checking quotes needs no internet; a full offline setup requires local models.

How it differs from other councils

The "several AIs deliberate" mechanic is already common. What sets Consilium apart isn't the number of voices. It's that a claim can be re-verified, and where it can't, the council honestly stays silent:

| | "Roleplay a sage" (one AI) | LLM-Council-style board | Persona board with a quote check (e.g. roast-room) | Consilium | |---|:---:|:---:|:---:|:---:| | Different lenses, disagreement as a feature | ± | ✅ | ✅ | ✅ | | Quote checked word-for-word against the corpus of the advisor it is attributed to | ✗ | ✗ | ± pooled corpus, after the session | ✅ per advisor, before output | | Honestly silent outside the corpus (fail-closed) | ✗ | ✗ | ✗ | ✅ | | Verdict computed by code, with caps for ruin risk and irreversible bets | ✗ | ✗ | ✅ | ✅ | | Quantifiable question → Monte Carlo (📐) | ✗ | ✗ | ✗ | ✅ | | Different models in the seats, on subscriptions you already have | ✗ | ± API key | ✗ | ✅ Claude Code / Codex / Kimi | | No separate key required by the project | ± | ± | ✅ | ✅ |

_{A "personal board of directors" is a mainstream practice (an HBR concept); the bet on grounding and citation transparency has been validated by both the market (Delphi, $16M from Sequoia) and academia (multi-persona debate, the ALCE benchmark). Our angle is rigor: a verifiable quote and an honest refusal.}

How it looks

<div align="center"> <img src="assets/demo-refusal-en.gif" width="760" alt="Live demo: Consilium refuses an invented quote and verifies a real passage against its source" />

_{Live run: an invented Aurelius quote is refused; a real passage is checked against its source. More scenarios — wrong attribution, Monte Carlo, cross-lingual: demo gallery →}

</div>

You ask in plain words:

"I'm juggling four directions at once. What should I focus on?"

And instead of one smooth, hedge-everything answer, you get a session where each advisor looks from their own vantage point, and they disagree:

Sun Tzu (the "Strategist" lens) 🟡 "Whoever is strong everywhere is strong nowhere. Of the four fronts, pick the one where you have the advantage, throw your weight there; hold the rest at a minimum."

Machiavelli 🟡 "Spread thin, you're weak on every front and vulnerable on all of them. The question isn't 'what to grow' but 'what you're willing to give up'. That is the decision."

Marcus Aurelius 🔵 "Let it be thy earnest and incessant care as a Roman and a man to perform whatsoever it is that thou art about" (Meditations, trans. Long). Do the thing in front of you wholly; four things at once is scattering. ↳ and ask him something that isn't in his texts, and he'll honestly stay silent instead of inventing a quote.

Next comes the synthesis (where they actually agree) and one concrete next step. Disagreement here is a feature: you see the decision from angles you'd have missed on your own. And if the question is quantifiable ("which is more worthwhile, X or Y"), the board will offer not to argue by eye but to calculate (see 📐 below).

_{The example is illustrative, and the advisors are AI representations built from texts, not the authors themselves. 🟡 = a thought in the author's spirit (the model reasons through their lens), 🔵 = a verbatim line with a source in the corpus. All examples are public-domain figures (Sun Tzu, Aurelius, Machiavelli, Epictetus); who sits at YOUR table is your call. Your real sessions are written to council/ locally, and never go into git (see technical design).}

What you can ask

No need to learn commands. Say "what can you do?" and the board will show a menu. For example:

• "What could go wrong with my launch?" a premortem: where it'll break, what to shore up in advance
• "What would Aurelius say about burnout?" a single advisor, strictly from his texts
• "Have Sun Tzu and Machiavelli argue about X" pit two viewpoints against each other
• "Which is more worthwhile, going back to a salaried job or sticking with my own thing?" 📐 a decision map: break it into numbers and calculate (rather than argue by eye)
• "Help me win this argument" a position breakdown like a chess engine: your moves, counters, an honest verdict
• "Am I contradicting myself?" a mirror: what you say vs. what you actually choose

Why you can trust this

This isn't "a chatbot playing sage." Every word is tagged by a protective contour.

The real proof isn't in the tone but in verifiability: a verbatim quote (🔵) is checked against the author's genuine corpus by code, word-for-word, and carries a source. If the exact line isn't found, the advisor honestly stays silent (fail-closed) instead of making it up. That's what separates a decision tool from "roleplay a sage": every claim can be re-checked.

| Marker | What it means | |:---:|---| | 🔵 | verbatim quote from the author's genuine corpus, verified word-for-word, with a source | | 🟢 | verbatim, but from commentary/interpretation (not in the author's own voice), with the commentator named | | 🟡 | in the spirit of the author, but not their exact words, honestly marked | | 📐 | calculation: your own numbers, run through Monte Carlo; not truth, not a quote, just your own model run N times | | abstention | question outside the corpus → the advisor stays silent instead of making things up |

Plus different lenses, not a chorus: each advisor keeps their own angle, and their disagreement is a working part, not a bug. You see the decision from sides you'd otherwise collapse into one.

The honesty contour itself is code, not a model: it checks every quote against its source on any machine, no keys, no cost. Without semantics only search precision gets weaker — honesty never does. Candidate relevance is scored by a two-phase gate: a model judges, code applies the threshold, so topically-close-but-not-actually-answering material won't slip through as 🔵. By default the host does that scoring — an interested party, which doctor labels honestly; want an independent judge, connect a local (ollama) or API backend, an explicit choice. The API backend is OpenRouter (openrouter.ai) with your own OPENROUTER_API_KEY: the query and candidate passages are sent there for scoring. Nothing leaves your machine unless you turn it on. The verbatim 🔵 gate never depends on the judge: code holds it.

Calculate, not just discuss: the 📐 decision map

The board has two modes. The first is a session (discuss, challenge, synthesize). The second kicks in on a quantifiable decision question ("which is more worthwhile", "is it worth it", "X or Y"): instead of an eyeballed answer, the board breaks the choice down into a decision map, that is options, quantities (your own numbers, elicited as three-point "worst / typical / best" estimates, to avoid anchoring), and formulas. Then comes deterministic Monte Carlo (code does the math, zero LLM in the calculation, same seed gives the same result): P(best option), a tornado sensitivity chart, what actually drives the outcome. A "do nothing" option is mandatory. Breaking it down with a premortem ("a year passed, it failed, why?") and a 2×2 on the key uncertainties is also something the board does. Everything sits under the 📐 label, next to 🔵/🟢/🟡 but never blended in: this isn't wisdom, it's your own model, run numerically. And if you log the decision, later the board will check the forecast against what actually happened (the outcome loop: calibrating your model, not "right or wrong guess").

By default, plainly human: the board answers in your language and gives a clean bottom line without extra numbers. A 🔵 quote stays in the original (so it can be verified), with a translation alongside it. Need the full breakdown (probabilities, robustness of the position, source-by-source markup), just say "show me the details."

Installation

Via Claude Code plugin (recommended)

In Claude Code:

/plugin marketplace add ilyautov/consilium-principis /plugin install consilium-principis@consilium-marketplace

Claude Code will spin up the MCP server and register the skill. Then say "where do I start", and the concierge will check readiness and assemble a starter board (Marcus Aurelius and Epictetus, public-domain).

Via skills.sh (CLI)

From the skills.sh registry, one command installs the thin onboarding funnel:

npx skills add ilyautov/consilium-principis/skills/consilium-connect

This installs only the consilium-connect guide sk