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/tonone-ai/tonone/driftgit clone --depth 1 https://github.com/tonone-ai/tononeWhat 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 | $0.00018 | $0.00552 |
| Opus 5 | $0.00009 | $0.00276 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 58 lines · 18 tokens per session scan A bab9d84b7e51
drift is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 16d ago), licensed MIT. It adds 18 tokens to every session and 552 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
streaming
Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…