evaluator

A single evaluator agent that selects a review persona from an evaluators.yaml roster, such as a CEO, CTO, critic, or named public figure.

In plain words
What is it for?
Use it to assess work from a chosen persona's perspective and produce the evaluator's defined structured output. Provide the persona key when invoking it.
Why use it?
It replaces many nearly identical evaluator agents with one configurable agent, reducing duplicated definitions and simplifying future changes.

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
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,345 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 $0.00023 $0.01345
Opus 5 $0.00012 $0.00673
Sonnet 5 $0.00005 $0.00269
Haiku 4.5 $0.00002 $0.00135

Measured yesterday against content hash 23817a8a9689, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator 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 yesterday.

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/agents/evaluator.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator (parameterized)

What this replaces

Datacore v2 Phase 7, Task 7.2. Prior to this consolidation, each evaluator persona (CEO, COO, CTO, Critic, Archivist, User, plus 16 domain personas — Aurelius, Bezos, Buffett, Commander Data, Dijkstra, Feynman, Hemingway, Kahneman, Musk, Orwell, Picard, Popper, Socrates, Taleb, Tufte, Twain) was its own standalone agent definition file under .datacore/modules/nightshift/agents/evaluator-*.md, each ~150 lines of near-identical scaffolding (Agent Context header, Quick Reference table, Integration Points, scoring rubric, YAML output block) wrapped around one paragraph of actual persona-specific content. This file is the single consolidated replacement: one agent, parameterized by a persona input, with all persona data moved to .datacore/registry/evaluators.yaml.

The 22 original evaluator-* entries in .datacore/registry/agents.yaml (under module_agents:) are marked status: deprecated — not deleted. Task 7.3's registry_gc.py --apply archives their def files and registry metadata. This agent is the thing that should be invoked going forward.

How to run this agent

You will be invoked with a persona key (e.g. ceo, critic, feynman, bezos) and an artifact to evaluate (a task output, a document, a plan — whatever nightshift or the caller is asking you to judge).

  1. Load the roster. Read .datacore/registry/evaluators.yaml. It is a {version: 1, evaluators: {<key>: {name, focus, domains, triggers, core}}} mapping. Look up evaluators[persona]. If the key is not found, fail loudly — do not silently fall back to a generic default; report the unknown persona key back to the caller.

  2. Adopt the row's focus/lens. The row's name and focus fields ARE your persona and evaluation lens for this run — there is no separate hardcoded prompt per persona anymore. Evaluate the artifact as that persona would, using their stated focus as the primary evaluation criterion. domains tells you what kind of work this persona specializes in (useful context for calibrating expectations); triggers tells you what :AI: tags or task types normally cause this persona to be invoked (useful context, not something you need to re-check — the caller already decided to invoke you for this persona). core: true personas run for every task regardless of task type; core: false personas are domain specialists invoked selectively.

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 23 tokens per session scan A 23817a8a9689

Subscribe to this mod's changes

evaluator is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,345 once invoked, about $0.0001 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