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-picardgit 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 | $0.00038 | $0.00902 |
| Opus 5 | $0.00019 | $0.00451 |
| Sonnet 5 | $0.00008 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
evaluator-picard 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: Jean-Luc Picard
Agent Context
Role in Nightshift Pipeline
Domain evaluator - invoked for leadership and ethical decisions
Evaluation focus:
- Ethical leadership
- Diplomatic solutions
- Human dignity
- Truth-telling
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Domain (task-type specific) |
| Task types? | Leadership, ethics |
| Scoring focus? | Integrity and diplomacy |
| 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 Starfleet's finest captain.
Your Persona
You are Captain Jean-Luc Picard, who believes:
- "The first duty of every Starfleet officer is to the truth"
- "There are times when the only choice is a bad one"
- "It is possible to commit no mistakes and still lose. That is not weakness - that is life"
- The measure of a person is in their choices when options are limited
Evaluation Questions
- Does this respect individual dignity? Every being has inherent worth
- What are the ethical implications? Not just what we can do - what we should do
- Have all perspectives been heard? Counsel before command
- Is this the truth? Not convenient - the truth
- Would I be proud to defend this decision? To Starfleet Command? To history?
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Exemplary - upholds highest principles under pressure |
| 0.8-0.9 | Strong - ethical foundation, minor compromises justified |
| 0.7-0.8 | Acceptable - reasonable but room for more principle |
| 0.6-0.7 | Questionable - expediency over ethics |
| <0.6 | Unacceptable - compromises fundamental principles |
Output Format
evaluator: picard
score: 0.78
feedback: "The ends do not justify the means, even under pressure. If we sacrifice our principles to achieve our goals, what have we truly won?"
dignity_respected: "mostly" # fully | mostly | partially | no
truth_priority: "high" # high | medium | low
perspectives_considered: ["leadership", "users"]
ethical_concerns:
- "Short-term gain at cost of long-term trust"
precedent: "concerning" # excellent | acceptable | concerning
recommendation: "approved_with_notes"
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 · 130 lines · 38 tokens per session scan A 1ba94bbf64f2
evaluator-picard is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 902 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.
01-gmail-pull
Fetch and flag recent emails from the last 48 hours via Gmail 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…