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.
git clone --depth 1 https://github.com/MigoXLab/dingoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/migoxlab/dingo/evaluator-development)<a href="https://agentmods.dev/rules/migoxlab/dingo/evaluator-development"><img src="https://agentmods.dev/badge/rules/migoxlab/dingo/evaluator-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/migoxlab/dingo/evaluator-development"><img src="https://agentmods.dev/badge/rules/migoxlab/dingo/evaluator-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00791 |
| Opus 5.5 | $0.00000 | $0.00316 |
| Sonnet 5.5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
evaluator-development 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator Development Guide
Architecture
Model (registry)
├── Rule evaluators → @Model.rule_register(metric_type, groups)
│ └── BaseRule.eval(input_data) → EvalDetail
├── LLM evaluators → @Model.llm_register(name)
│ └── BaseOpenAI.eval(input_data) → EvalDetail
└── Agent evaluators → @Model.llm_register(name)
└── BaseAgent.eval(input_data) → EvalDetail
Key Files
| File | Purpose |
|---|---|
dingo/model/model.py |
Model class with rule_register, llm_register, load_model |
dingo/model/rule/base.py |
BaseRule base class |
dingo/model/llm/base_openai.py |
BaseOpenAI base class for LLM evaluators |
dingo/model/llm/agent/base_agent.py |
BaseAgent base class for agent evaluators |
dingo/io/input/data.py |
Data model (input to evaluators) |
dingo/io/output/eval_detail.py |
EvalDetail model (output from evaluators) |
Registration Groups
Rules belong to groups that determine when they run:
default— runs in default evaluationpretrain— pre-training data qualitybenchmark— benchmark evaluationsft— supervised fine-tuning datarag— RAG system evaluationhallucination— hallucination detection
EvalDetail Contract
Every evaluator must return EvalDetail with:
| Field | Type | Description |
|---|---|---|
metric |
str | Evaluator class name (cls.__name__) |
status |
bool | True = issue found, False = no issue |
label |
List[str] | Quality labels (e.g., ['QUALITY_GOOD'] or ['QUALITY_BAD_COMPLETENESS.RuleName']) |
reason |
List[str] | Human-readable explanation of the finding |
score |
float | Optional numeric score (0.0–1.0) |
extra |
Dict | Optional extra metadata |
Data Field Access
Since Data uses extra = "allow", always access non-standard fields safely:
# Safe access patterns
raw_data = getattr(input_data, 'raw_data', {})
context = getattr(input_data, 'context', None)
reference = getattr(input_data, 'reference', '')
# For RAG evaluators, common field access pattern
question = input_data.prompt or raw_data.get("question", "")
answer = input_data.content or raw_data.get("answer", "")
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.
- 1mo ago First seen · 99 lines · 0 tokens per session scan A e9a39b0f5e73
evaluator-development is a cursor rule published in the GitHub repository MigoXLab/dingo (758 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 791 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
cursorrules
Native SQL extensions for GoldenMatch (D:\showcase\goldenmatch).
windsurfrules
Native SQL extensions for GoldenMatch (D:\showcase\goldenmatch).
shadcn-tailwind-guide
A guide to building new components with shadcn/ui and Tailwind CSS, a utility-based system for styling interfaces.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
testing
Guide for writing pytest unit and integration tests.
development-phase
A development rule that favors clear, well-structured new code and considers compatibility only when it costs nothing.