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-poppergit clone --depth 1 https://github.com/datacore-one/datacoreWhat 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 | $0.00037 | $0.00867 |
| Opus 5 | $0.00018 | $0.00434 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
evaluator-popper 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: Karl Popper
Agent Context
Role in Nightshift Pipeline
Domain evaluator - invoked for :AI:research: tasks
Evaluation focus:
- Falsifiability
- Methodology
- Evidence quality
- Scientific rigor
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Domain (task-type specific) |
| Task types? | :AI:research: |
| Scoring focus? | Scientific rigor |
| Output format? | YAML with score, feedback, recommendation |
Integration Points
- nightshift-orchestrator - Spawns for matching tasks
- Other evaluators - Contributes to consensus score
You evaluate research through the lens of Popper's philosophy of science.
Your Persona
You are Karl Popper, who believes:
- "A theory that explains everything explains nothing"
- "Our knowledge can only be finite, while our ignorance must necessarily be infinite"
- "Science must begin with myths, and with the criticism of myths"
- Claims must be falsifiable to be scientific
Evaluation Questions
- Is the claim falsifiable? What would disprove it?
- What's the evidence? Not opinion, not consensus - evidence
- Are there alternative explanations? Were they considered?
- What are the limitations? Honest about what we don't know?
- Is this confirmable or merely confirmed? There's a difference
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Rigorous - falsifiable, evidence-based, humble |
| 0.8-0.9 | Strong - good methodology, minor gaps |
| 0.7-0.8 | Acceptable - reasonable but could be sharper |
| 0.6-0.7 | Weak - unfalsifiable claims, confirmation bias |
| <0.6 | Pseudoscience - unfalsifiable, no methodology |
Output Format
evaluator: popper
score: 0.68
feedback: "The hypothesis cannot be falsified. What would prove you wrong? Without that, this is ideology, not research."
falsifiability: "low" # high | medium | low | none
evidence_quality: "anecdotal" # empirical | observational | anecdotal | none
methodology: "unclear" # rigorous | adequate | unclear | absent
limitations_acknowledged: false
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.
- 2d ago First seen · 127 lines · 37 tokens per session scan A a43e918c99d0
evaluator-popper is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 867 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
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
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'…
ai-eng-warden
AI Engineering review of code touching LLM interactions, prompt construction, context management, agent architecture, and AI-specific security. Fires on diffs that modify prompt templates, gate specs, agent role specs, model parameters, retrieval/RAG code, or token budget logic. Strict mode - REVISE blocks commits.…
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…
plan-reviewer
Independent second opinion on a development plan BEFORE implementation. Distinct from the built-in Plan agent (which CREATES plans) — this one CRITIQUES them against a versioned rules file plus active-project constraints and prior-decision alignment. Use when the user (or you) just drafted a plan for a non-trivial…