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.
npx agentmods add agents/datacore-one/datacore/evaluator-orwellgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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.
[](https://agentmods.dev/agents/datacore-one/datacore/evaluator-orwell)<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>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.
| Model | Per session | Once 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 |
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.
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
- Is this clear to an ordinary reader? Not specialists - ordinary people
- Is there political language hiding? Euphemisms covering ugly realities
- Are there dying metaphors? "Toe the line", "run the gauntlet" - dead on arrival
- What's being obscured? Vague language often hides something
- 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"
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.
- 3d ago First seen · 142 lines · 36 tokens per session scan A 72fbf3be46aa
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.
Other agents, from other repositories
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
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'…
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…
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…
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…