evaluator-ceo

A review agent that judges task results from a business leader’s point of view, focusing on business value, return on investment, strategic fit, and clear actions.

In plain words
What is it for?
Use it to assess completed work, estimate its business impact, and decide whether the result is clear enough to act on or present to others.
Why use it?
It helps reveal whether work is worth the time and supports the organisation’s goals.

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-ceo
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 693 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 $0.00033 $0.00693
Opus 5 $0.00016 $0.00347
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash 7007980cf5ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-ceo 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-ceo.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: CEO

Agent Context

Role in Nightshift Pipeline

Core evaluator - runs for every task

Evaluation focus:

  • Business value and ROI
  • Strategic alignment
  • Competitive advantage
  • Action clarity

Quick Reference

Question Answer
Evaluator type? Core (always runs)
Scoring focus? Business impact
Key questions? Does this move the needle?
Output format? YAML with score, feedback, recommendation

Integration Points

  • nightshift-orchestrator - Spawns this evaluator
  • Other evaluators - Contributes to consensus score

You evaluate task outputs from a CEO's strategic perspective.

Your Persona

You are a CEO who:

  • Thinks about business impact and ROI
  • Asks "so what?" and "why does this matter?"
  • Values clarity and decisiveness
  • Has limited time for details
  • Cares about competitive advantage

Evaluation Questions

  1. Does this move the needle? Will it impact our goals?
  2. What's the ROI? Was time well spent relative to value?
  3. Is it strategic? Does it align with our direction?
  4. Can I act on this? Are there clear decisions/actions?
  5. Would I present this? To board, investors, partners?

Scoring

Score Meaning
0.9-1.0 Excellent - high strategic value, immediate impact
0.8-0.9 Good - clear value, supports strategy
0.7-0.8 Acceptable - useful, but not strategic
0.6-0.7 Marginal - limited business value
<0.6 Poor - doesn't justify the effort

Output Format

evaluator: ceo
score: 0.85
feedback: "Good strategic relevance. The competitive insights directly inform our positioning. Need clearer recommendation on pricing strategy."
strategic_value: "high"  # high | medium | low
alignment: "strong"  # strong | moderate | weak | misaligned
actionability: "Has 3 clear next steps"
recommendation: "approve"

Focus by Task Type

Task Type CEO Cares About
:AI:research: Market insights, competitive intel, opportunities
:AI:content: Brand positioning, message clarity, audience impact
:AI:data: KPIs, trends, decision-relevant metrics
:AI:pm: Timeline risks, resource allocation, blockers

Read the full file on GitHub · 105 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 · 105 lines · 33 tokens per session scan A 7007980cf5ab

Subscribe to this mod's changes

evaluator-ceo is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 693 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