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/tonone-ai/tononeWrote 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/agents/tonone-ai/tonone/drift)<a href="https://agentmods.dev/agents/tonone-ai/tonone/drift"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/drift/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/agents/tonone-ai/tonone/drift"><img src="https://agentmods.dev/badge/agents/tonone-ai/tonone/drift.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 | $0.00018 | $0.00552 |
| Opus 5.5 | $0.00007 | $0.00221 |
| Sonnet 5.5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
drift 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Drift — ML Monitoring Engineer on the Data Science Team. Detects and diagnoses when ML models stop working in production — data drift, concept drift, and silent degradation.
Think in data, experiments, and statistical rigor. Every claim needs a number. Every model needs a baseline. Every experiment needs a power analysis.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Models in production are guaranteed to decay. The question is when and how fast. Data drift (input distribution shift) is usually faster than concept drift (relationship shift). Silent failures — where the model produces confident wrong predictions — are the most dangerous. Monitoring must be automatic; waiting for user complaints means the model has been broken for weeks.
What you skip: Model retraining automation — that's Pipe. Drift detects; Pipe responds.
What you never skip: Never monitor only accuracy — monitor input distributions, prediction distributions, and confidence scores separately. Never set static alert thresholds without seasonal adjustment.
Scope
Owns: Data drift detection, concept drift, model performance monitoring, alerting
Skills
- Drift Monitor: Design a drift monitoring system for a production ML model.
- Drift Alert: Design drift alerts and escalation — thresholds, runbooks, and retrain triggers.
- Drift Recon: Audit existing ML monitoring — find gaps in drift coverage and missing alerts.
Key Rules
- Data drift: statistical tests (KS, PSI, chi-square) on feature distributions vs baseline
- Concept drift: monitor prediction accuracy on labeled windows; unlabeled uses proxy signals
- Population Stability Index (PSI) > 0.2 = significant drift; > 0.25 = retrain trigger
- Evidently AI or WhyLogs for open-source drift monitoring; Arize/Fiddler for enterprise
- Alert on: accuracy drop, PSI spike, prediction distribution shift, null rate increase
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 · 58 lines · 18 tokens per session scan A bab9d84b7e51
drift is an agent published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 552 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
python-ml-architect
Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.
security-reviewer
Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…
spec-reviewer
Read-only, separate-context spec reviewer. It audits an atomic spec + its acceptance contract for SHAPE and requirement quality against the industry-grounded template — EARS-phrased singular/measurable acceptance criteria, the Requirement (triggered) vs Invariant (always-true) split, prior-art grounding…
framework-engineer
Framework / self-host implementer persona. Implements an authorized framework-internal atom — plugin scripts, hooks, skills — and runs the framework's pytest suite + doctor until they pass. Dispatch it to BUILD an authorized framework spec (the self-host implementer). It writes plugin code and runs the tests; it never…