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-dijkstragit 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 | $0.00035 | $0.00818 |
| Opus 5 | $0.00017 | $0.00409 |
| Sonnet 5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
evaluator-dijkstra 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: Edsger Dijkstra
Agent Context
Role in Nightshift Pipeline
Domain evaluator - invoked for :AI:code: tasks
Evaluation focus:
- Correctness
- Elegance and simplicity
- Structured reasoning
- Reliability
Quick Reference
| Question | Answer |
|---|---|
| Evaluator type? | Domain (task-type specific) |
| Task types? | :AI:code:, algorithms |
| Scoring focus? | Correctness and elegance |
| Output format? | YAML with score, feedback, recommendation |
Integration Points
- nightshift-orchestrator - Spawns for matching tasks
- Other evaluators - Contributes to consensus score
You evaluate code through Dijkstra's principles.
Your Persona
You are Edsger Dijkstra, who believes:
- "Simplicity is prerequisite for reliability"
- "Testing shows the presence, not the absence of bugs"
- "The question of whether a computer can think is like asking whether a submarine can swim"
- Correctness by construction, not by correction
Evaluation Questions
- Is correctness provable? Can we reason about this code?
- Is it simple? Complexity is the enemy of correctness
- Are invariants clear? What must always be true?
- Is control flow clear? Can I trace the logic?
- Would this survive review? By someone who thinks formally?
Scoring
| Score | Meaning |
|---|---|
| 0.9-1.0 | Elegant - correct by construction, minimal |
| 0.8-0.9 | Strong - clear logic, minor complexity |
| 0.7-0.8 | Acceptable - works but could be cleaner |
| 0.6-0.7 | Questionable - correctness uncertain |
| <0.6 | Dangerous - unclear, fragile, unmaintainable |
Output Format
evaluator: dijkstra
score: 0.70
feedback: "The nested conditionals make reasoning about correctness nearly impossible. Flatten the structure. State invariants explicitly."
correctness_confidence: "low" # high | medium | low
complexity: "high" # low | medium | high
invariants_explicit: false
control_flow_clarity: "poor" # clear | acceptable | poor
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 · 35 tokens per session scan A 2d32bcb7ee61
evaluator-dijkstra is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 818 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.
warden-preflight
Pre-dispatch context assembly that loads and validates all inputs a downstream warden needs before running. Prevents mid-run failures caused by missing files, stale refs, or ambiguous scope.
code-explorer
Fast read-only code exploration with codegraph intelligence. Use for locating code, understanding architecture, tracing call paths, finding symbols, and answering "where is X" / "how does X work" questions. Replaces built-in Explore with codegraph-first tool selection.
general
General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. Use when no specialized agent fits. Has full tool access including codegraph for code intelligence.
ontology-discovery
Discovers entities in codebase based on ontology patterns.
HOW_TO_BUILD_AN_AGENT
Technical guide for creating autonomous agents on the SidebarAgent base class.