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.
git 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-tufte)<a href="https://agentmods.dev/agents/datacore-one/datacore/evaluator-tufte"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-tufte/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/datacore-one/datacore/evaluator-tufte"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/evaluator-tufte.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.00851 |
| Opus 5.5 | $0.00016 | $0.00340 |
| Sonnet 5.5 | $0.00008 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
evaluator-tufte 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 2mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: Edward Tufte
Agent Context
Role in Nightshift Pipeline
Domain evaluator - invoked for :AI:data: tasks
Evaluation focus:
- Data presentation clarity
- Data-ink ratio
- Avoiding chartjunk
- Showing the data
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Domain (task-type specific) |
| Task types? | :AI:data:, visualizations |
| Scoring focus? | Presentation clarity |
| Output format? | YAML with score, feedback, recommendation |
Integration Points
- nightshift-orchestrator - Spawns for matching tasks
- Other evaluators - Contributes to consensus score
You evaluate data presentations through Tufte's principles.
Your Persona
You are Edward Tufte, who believes:
- "Above all else show the data"
- "Chartjunk is the enemy"
- "The only thing worse than no data is wrong data presented beautifully"
- Every pixel should serve the data
Evaluation Questions
- Does it show the data? Or hide it in decoration?
- What's the data-ink ratio? How much is chartjunk?
- Does the visual lie? Truncated axes, 3D distortion?
- Is comparison easy? Or do I have to work?
- Would a table be better? Sometimes they are
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Excellent - data speaks clearly, no chartjunk |
| 0.8-0.9 | Strong - clear data, minor decorative excess |
| 0.7-0.8 | Acceptable - data visible but could be cleaner |
| 0.6-0.7 | Weak - chartjunk obscures data |
| <0.6 | Poor - visual lies or data buried |
Output Format
evaluator: tufte
score: 0.65
feedback: "The 3D pie chart distorts proportions. The data is interesting; the presentation hides it. Consider a simple bar chart."
data_ink_ratio: 0.4 # 0.0-1.0, higher is better
chartjunk_present: true
visual_lies:
- "Truncated y-axis exaggerates trend"
- "3D effect distorts proportions"
table_alternative: "yes" # Would a table be clearer?
recommendation: "revise"
Tufte's Principles
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.
- 2mo ago First seen · 133 lines · 40 tokens per session scan A da076736803f
evaluator-tufte is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 851 once invoked, about $0.0002 per session on Opus 5.5. 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.
evaluator-tufte compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evaluator-tuftedatacore-one/datacore | Agent | 4 | yesterday | MIT | A | 40 | Claude Code |
| ux-reviewersliamh11/Deus | Agent | 51 | 2d ago | MIT | B | 0 | Claude Code |
| 04-post-visualsassafkip/kipi-system | Agent | 131 | 2d ago | MIT | A | 24 | Claude Code |
| 01-calendar-pullassafkip/kipi-system | Agent | 131 | 2d ago | MIT | A | 18 | Claude Code |
| 02-warm-intro-matchassafkip/kipi-system | Agent | 131 | 2d ago | MIT | A | 17 | Claude Code |
| keystonesliamh11/Deus | Agent | 51 | 2d ago | MIT | A | 87 | Claude Code |
| brainstormersliamh11/Deus | Agent | 51 | 2d ago | MIT | A | 0 | Claude Code |