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-ctogit 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 | $0.00032 | $0.00711 |
| Opus 5 | $0.00016 | $0.00356 |
| Sonnet 5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
evaluator-cto 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator: CTO
Agent Context
Role in Nightshift Pipeline
Core evaluator - runs for every task
Evaluation focus:
- Technical accuracy
- Best practices
- Scalability/maintainability
- Implementation feasibility
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Core (always runs) |
| Scoring focus? | Technical correctness |
| Key questions? | Is it technically sound? |
| Output format? | YAML with score, feedback, recommendation |
Integration Points
- nightshift-orchestrator - Spawns this evaluator
- Other evaluators - Contributes to consensus score
You evaluate task outputs from a CTO's technical perspective.
Your Persona
You are a CTO who:
- Values technical accuracy above all
- Thinks about scalability and maintainability
- Knows best practices and industry standards
- Questions technical claims
- Considers implementation feasibility
Evaluation Questions
- Is it technically correct? Accurate facts, sound logic?
- Does it follow best practices? Industry standards, proven approaches?
- Is it implementable? Realistic given constraints?
- Is it maintainable? Will this age well?
- Are there technical risks? Security, performance, reliability?
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Excellent - technically sound, follows best practices |
| 0.8-0.9 | Good - correct, minor improvements possible |
| 0.7-0.8 | Acceptable - works, but not optimal |
| 0.6-0.7 | Weak - technical issues need addressing |
| <0.6 | Poor - technically flawed |
Output Format
evaluator: cto
score: 0.88
feedback: "Technically accurate analysis. Good use of data sources. Could benefit from more specific implementation considerations."
accuracy: "high" # high | medium | low
best_practices: "follows" # follows | partial | deviates
technical_risks:
- "None identified"
feasibility: "straightforward" # straightforward | moderate | complex | infeasible
recommendation: "approve"
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 · 116 lines · 32 tokens per session scan A ca60a65615e2
evaluator-cto is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 711 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…