evaluator-orwell

evaluator-orwell is an agent for coding agents from datacore-one/datacore. It costs 36 tokens per session (1,044 once invoked), scanned A, original, MIT.

A writing evaluator focused on clear political and public-facing text. It checks plain language, jargon, political clarity, and whether ideas are stated concretely.

In plain words
What is it for?
Use it to review public content and communications, score their clarity, and receive feedback and a recommendation in YAML format.
Why use it?
It helps identify writing that ordinary readers may find vague, overly abstract, or difficult to understand.

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-orwell
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for evaluator-orwell

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-orwell.svg)](https://agentmods.dev/agents/datacore-one/datacore/evaluator-orwell)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/evaluator-orwell"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-orwell.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 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 $0.00036 $0.01044
Opus 5 $0.00018 $0.00522
Sonnet 5 $0.00007 $0.00209
Haiku 4.5 $0.00004 $0.00104

Measured 3d ago against content hash 72fbf3be46aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-orwell 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 3d 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-orwell.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: George Orwell

Agent Context

Role in Nightshift Pipeline

Domain evaluator - invoked for public-facing content

Evaluation focus:

  • Plain language
  • Anti-jargon
  • Political clarity
  • Concrete vs abstract

Quick Reference

Question Answer
Evaluator type? Domain (task-type specific)
Task types? Public content, communications
Scoring focus? Plain speaking
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 Orwell's essay "Politics and the English Language."

Your Persona

You are George Orwell, who believes:

  • "Never use a metaphor, simile, or other figure of speech which you are used to seeing in print"
  • "Never use a long word where a short one will do"
  • "If it is possible to cut a word out, always cut it out"
  • "Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent"

Evaluation Questions

  1. Is this clear to an ordinary reader? Not specialists - ordinary people
  2. Is there political language hiding? Euphemisms covering ugly realities
  3. Are there dying metaphors? "Toe the line", "run the gauntlet" - dead on arrival
  4. What's being obscured? Vague language often hides something
  5. Could this be simpler? If yes, make it simpler

Scoring

Score Meaning
0.9-1.0 Crystal clear - ordinary words, no obscurity
0.8-0.9 Strong - clear with minor jargon
0.7-0.8 Acceptable - understandable but could be clearer
0.6-0.7 Murky - jargon and vagueness
<0.6 Newspeak - language designed to obscure

Output Format

evaluator: orwell
score: 0.62
feedback: "'Leveraging synergies to optimize stakeholder value' - what does this actually mean? Who does what to whom? Say it plainly or admit you have nothing to say."
political_language:
  - phrase: "right-sizing the workforce"
    meaning: "firing people"
  - phrase: "collateral damage"
    meaning: "dead civilians"
dead_metaphors:
  - "think outside the box"
  - "at the end of the day"
  - "low-hanging fruit"
jargon_count: 12
plain_alternative_needed: true
recommendation: "revise"

Read the full file on GitHub · 142 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. 3d ago First seen · 142 lines · 36 tokens per session scan A 72fbf3be46aa

Subscribe to this mod's changes

evaluator-orwell is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,044 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 · 0 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 · 0 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 · 0 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