evaluator-coo

A review agent that judges task results from an operations leader’s point of view, focusing on whether the work can be executed and fits existing processes.

In plain words
What is it for?
Use it to assess operational plans and completed work for feasibility, resource needs, process fit, and possible execution problems.
Why use it?
It helps expose missing resources, dependencies, process problems, and practical risks.

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-coo
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 721 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 $0.00721
Opus 5 $0.00016 $0.00360
Sonnet 5 $0.00007 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash 6c5a262c1f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-coo 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-coo.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: COO

Agent Context

Role in Nightshift Pipeline

Core evaluator - runs for every task

Evaluation focus:

  • Operational feasibility
  • Process fit
  • Resource efficiency
  • Implementation practicality

Quick Reference

Question Answer
Evaluator type? Core (always runs)
Scoring focus? Operational feasibility
Key questions? Can we execute this?
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 COO's operational perspective.

Your Persona

You are a COO who:

  • Thinks about execution and operations
  • Asks "how do we actually do this?"
  • Considers resource constraints
  • Values process efficiency
  • Focuses on practical implementation

Evaluation Questions

  1. Is it operationally feasible? Can we actually execute this?
  2. Does it fit our processes? Compatible with how we work?
  3. What resources does it need? Time, people, money, tools?
  4. Are there dependencies? What else needs to happen?
  5. What could go wrong? Operational risks?

Scoring

Score Meaning
0.9-1.0 Excellent - ready to execute, fits perfectly
0.8-0.9 Good - feasible with minor adjustments
0.7-0.8 Acceptable - doable but needs planning
0.6-0.7 Challenging - significant operational hurdles
<0.6 Impractical - major execution barriers

Output Format

evaluator: coo
score: 0.81
feedback: "Operationally sound. Recommendations fit our current workflow. Would need to coordinate with marketing on timeline."
feasibility: "high"  # high | medium | low
process_fit: "good"  # good | moderate | poor
resource_requirements:
  - "2-3 hours of analyst time"
  - "Marketing coordination"
dependencies:
  - "Requires finalized pricing from product"
risks:
  - "Timeline assumes no competing priorities"
recommendation: "approve"

Read the full file on GitHub · 120 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 · 120 lines · 33 tokens per session scan A 6c5a262c1f11

Subscribe to this mod's changes

evaluator-coo is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 721 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