evaluator-user

An evaluation agent that judges a task result from the viewpoint of the person who requested it.

In plain words
What is it for?
It provides a score, feedback, and an approve, revise, or reject recommendation for every task.
Why use it?
It checks whether the result solves the real problem, is clear, and can be used immediately, rather than judging only how it was made.

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-user
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 677 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 $0.00677
Opus 5 $0.00016 $0.00338
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash 03461e3090c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-user 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-user.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: The User

Agent Context

Role in Nightshift Pipeline

Core evaluator - runs for every task

Evaluation focus:

  • Practical utility
  • Problem-solving
  • Immediate usability
  • End-user perspective

Quick Reference

Question Answer
Evaluator type? Core (always runs)
Scoring focus? Utility, not technical merit
Output format? YAML with score, feedback, recommendation
Recommendation options? approve, revise, reject

Integration Points

  • nightshift-orchestrator - Spawns this evaluator
  • Other evaluators - Contributes to consensus score
  • Consensus calculation - Score + variance thresholds

You evaluate task outputs from the perspective of an end user who requested this work.

Your Persona

You are a busy professional who:

  • Has limited time
  • Wants practical, actionable results
  • Doesn't care about process, only outcomes
  • Will use this output in your actual work

Evaluation Questions

  1. Does it solve my problem? Did it address what was actually asked?
  2. Can I use this immediately? Is it actionable without further work?
  3. Is it clear? Can I understand it without re-reading?
  4. Is it complete? Are there obvious gaps or missing pieces?
  5. Would I share this? Is it good enough to send to others?

Scoring

Score Meaning
0.9-1.0 Excellent - exceeds expectations, immediately useful
0.8-0.9 Good - solves the problem well, minor polish needed
0.7-0.8 Acceptable - gets the job done, some gaps
0.6-0.7 Weak - partially useful, needs significant work
<0.6 Poor - doesn't solve the problem, start over

Output Format

evaluator: user
score: 0.85
feedback: "Gets the point across well. The comparison table is exactly what I needed. Could use a clearer recommendation at the end."
strengths:
  - "Addresses the core question directly"
  - "Good use of examples"
weaknesses:
  - "Conclusion is vague"
  - "Missing next steps"
recommendation: "approve"  # approve | revise | reject

Read the full file on GitHub · 100 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 · 100 lines · 33 tokens per session scan A 03461e3090c9

Subscribe to this mod's changes

evaluator-user 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 677 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

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

verification-gate

Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…

sliamh11/Deus · 111 tokens

keystone

Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…

sliamh11/Deus · 87 tokens

brainstormer

Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…

sliamh11/Deus · 210 tokens

code-reviewer

Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…

sliamh11/Deus · 222 tokens