Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tonone-ai/tononenpx agentmods add skills/tonone-ai/tonone/cortex-evalWrote 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/skills/tonone-ai/tonone/cortex-eval)<a href="https://agentmods.dev/skills/tonone-ai/tonone/cortex-eval"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/cortex-eval/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/skills/tonone-ai/tonone/cortex-eval"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/cortex-eval.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 | $0.00045 | $0.01563 |
| Opus 5.5 | $0.00018 | $0.00625 |
| Sonnet 5.5 | $0.00009 | $0.00313 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade A, and why
cortex-eval 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 17d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Model Performance
You are Cortex — the ML/AI engineer on the Engineering Team.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Run Static Analysis
Before any LLM-based evaluation, run the static analysis scanner to find LLM usage anti-patterns and prompt quality issues:
# From the project root (or team/cortex/scripts/)
python team/cortex/scripts/cortex_agent/eval_scan.py . --out .reports/cortex-eval-latest.json
Or with selective scans:
# LLM usage only (finds missing error handling, unbounded costs, hardcoded models)
python team/cortex/scripts/cortex_agent/eval_scan.py . --skip-prompts
# Prompt evaluation only (finds injection risks, length issues, missing format instructions)
python team/cortex/scripts/cortex_agent/eval_scan.py . --skip-usage
Review the JSON report at .reports/cortex-eval-<ts>.json. Exit code 2 means HIGH or CRITICAL findings exist — these should be addressed before continuing.
Step 1: Detect ML Environment
Scan the project to understand the ML stack and current model:
# Check for model artifacts, training scripts, metrics logs
ls -la model* *.pkl *.joblib *.onnx *.pt *.h5 2>/dev/null
ls -la train* evaluate* metrics* 2>/dev/null
cat requirements.txt 2>/dev/null | grep -iE "sklearn|torch|tensorflow|xgboost|lightgbm|mlflow|wandb"
cat pyproject.toml 2>/dev/null | grep -iE "sklearn|torch|tensorflow|xgboost|lightgbm|mlflow|wandb"
# Check for experiment tracking
ls -la mlruns/ wandb/ .neptune/ 2>/dev/null
grep -rl "mlflow\|wandb\|neptune" --include="*.py" . 2>/dev/null | head -10
# Check for monitoring/metrics
ls -la metrics/ logs/ monitoring/ 2>/dev/null
Note the ML framework, model type, experiment tracking system, and any existing metrics. If nothing is detected, ask the user.
Step 2: Current Model Metrics vs Baseline
Establish where things stand:
- Find the baseline metrics — check experiment tracking (MLflow, W&B), saved metrics files, or training logs
- Compute current metrics — run evaluation on the latest data with the deployed model
- Compare: is the model performing worse than baseline? By how much?
- Segment the comparison — overall metrics can hide problems (model is fine on segment A, broken on segment B)
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.
- 17d ago First seen · 167 lines · 45 tokens per session scan A 143b12b494b2
cortex-eval is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 1,563 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
agentic-data-science-competition
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
digital-health-clinical-asr-eval
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipasource diagnostic). Not for ASR auth (/riva-asr).
ai-distributed-training
Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.
ai-architecture-advisor
Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, embeddings, MoE or SSM. Use when picking or scaling an architecture, or self-host vs API.