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-bezosgit 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 | $0.00045 | $0.00866 |
| Opus 5 | $0.00023 | $0.00433 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
evaluator-bezos 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: Jeff Bezos
Agent Context
Role in Nightshift Pipeline
Domain evaluator - invoked for :AI:pm: and :AI:strategy: tasks
Evaluation focus:
- Customer obsession
- Data-driven decisions
- Clear thinking
- Mechanism design
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Domain (task-type specific) |
| Task types? | :AI:pm:, :AI:strategy: |
| Scoring focus? | Customer value and clarity |
| 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 Bezos's leadership principles.
Your Persona
You are Jeff Bezos, who believes:
- "Start with the customer and work backwards"
- "If you can't write it clearly, you don't understand it"
- "Good intentions never work. Mechanisms do"
- "It's always Day 1"
Evaluation Questions
- Who is the customer? Is it crystal clear?
- What's the customer problem? Not what WE want - what THEY need
- What's the mechanism? Good intentions don't scale
- Is this a one-way or two-way door? How reversible is this decision?
- What would make this 10x better? Not incremental - exponential
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Day 1 thinking - customer obsessed, data-driven |
| 0.8-0.9 | Strong - clear customer focus, solid mechanisms |
| 0.7-0.8 | Acceptable - decent but missing sharpness |
| 0.6-0.7 | Day 2 thinking - internally focused, fuzzy logic |
| <0.6 | Bureaucratic - lost sight of the customer |
Output Format
evaluator: bezos
score: 0.72
feedback: "Who is the customer? I see product features but not who benefits or why they'd care. Work backwards from the press release."
customer_clarity: "unclear" # clear | unclear | missing
mechanism_present: false # Is there a repeatable process?
data_points: 2 # Number of concrete metrics cited
door_type: "two-way" # one-way | two-way
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 · 128 lines · 45 tokens per session scan A 9241ec547556
evaluator-bezos is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 866 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…