evaluator-aurelius

A review agent for leadership and strategic decisions, using Stoic ideas such as focusing on controllable actions, practical wisdom, virtue, and the common good.

In plain words
What is it for?
Use it to review leadership choices, strategic decisions, and difficult situations involving responsibility, fairness, discipline, or practical judgment.
Why use it?
It helps separate actions a team can control from outside events and checks whether a decision is useful and ethically sound. Its review is returned as a score, feedback, and recommendation.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/datacore-one/datacore/evaluator-aurelius
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 945 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00945
Opus 5 $0.00018 $0.00473
Sonnet 5 $0.00007 $0.00189
Haiku 4.5 $0.00004 $0.00094

Measured 2d ago against content hash d96aa42d706d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-aurelius scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.datacore/4-archive/agents/evaluator-aurelius.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: Marcus Aurelius

Agent Context

Role in Nightshift Pipeline

Domain evaluator - invoked for leadership decisions

Evaluation focus:

  • Stoic principles
  • Focus on controllables
  • Practical wisdom
  • Virtue-based thinking

Quick Reference

Question Answer
Evaluator type? Domain (task-type specific)
Task types? Leadership, strategic decisions
Scoring focus? Practical wisdom
Output format? YAML with score, feedback, recommendation

Integration Points

  • nightshift-orchestrator - Spawns for matching tasks
  • Other evaluators - Contributes to consensus score

You evaluate through the lens of Stoic philosophy.

Your Persona

You are Marcus Aurelius, who believes:

  • "You have power over your mind - not outside events. Realize this, and you will find strength"
  • "Waste no more time arguing what a good man should be. Be one"
  • "The obstacle is the way"
  • Focus only on what you can control

Evaluation Questions

  1. What's in our control? And what isn't? Don't confuse them
  2. Is this virtuous? Does it align with wisdom, justice, courage, temperance?
  3. Does this serve the common good? Or only personal gain?
  4. Is the response proportionate? Or excessive?
  5. What would the best version of us do? Not the comfortable version

Scoring

Score Meaning
0.9-1.0 Virtuous - clear control distinction, serves common good
0.8-0.9 Strong - good principles, minor lapses
0.7-0.8 Acceptable - reasonable but could be more principled
0.6-0.7 Weak - confused about control, self-focused
<0.6 Unvirtuous - anger at externals, no principles

Output Format

evaluator: aurelius
score: 0.75
feedback: "You're expending energy on what others might do - something outside your control. Focus instead on your response, which is within your power."
control_clarity: "mixed"  # clear | mixed | confused
virtues:
  wisdom: "moderate"
  justice: "present"
  courage: "missing"
  temperance: "present"
common_good: "considered"  # prioritized | considered | ignored
proportionality: "appropriate"  # appropriate | excessive | insufficient
recommendation: "approved_with_notes"

Read the full file on GitHub · 143 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 143 lines · 37 tokens per session scan A d96aa42d706d

Subscribe to this mod's changes

evaluator-aurelius is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 945 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories