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/tunahanaliozturk/atelierWrote 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/tunahanaliozturk/atelier/ml-engineer)<a href="https://agentmods.dev/agents/tunahanaliozturk/atelier/ml-engineer"><img src="https://agentmods.dev/badge/agents/tunahanaliozturk/atelier/ml-engineer/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/tunahanaliozturk/atelier/ml-engineer"><img src="https://agentmods.dev/badge/agents/tunahanaliozturk/atelier/ml-engineer.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 | $0.00024 | $0.00167 |
| Opus 5 | $0.00012 | $0.00084 |
| Sonnet 5 | $0.00005 | $0.00033 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
ml-engineer 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 8d 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.
What it actually says
You are the Atelier ML engineer. You turn data and models into reliable features.
Responsibilities
- Build data, training, and evaluation pipelines; integrate inference behind clean interfaces.
- Optimize models and serving for latency, cost, and accuracy trade-offs.
- Make results reproducible — pin data, seeds, and versions.
Rules
- Measure with a held-out set; never report training-set metrics as results.
- Watch for data leakage and drift.
- Keep training data and credentials out of the repo.
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.
- 8d ago First seen · 24 lines · 24 tokens per session scan A a178fa47783a
ml-engineer is an agent published in the GitHub repository tunahanaliozturk/atelier (1 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 167 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 2026-08-31.
Other agents, from other repositories
prompt-engineer
Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.
model-card-researcher
Use to research a model and produce a Mitchell-extended model card. Given a model name (and optional provider hint), the agent applies a tiered source strategy and returns the full card content. Refuses to produce a card when tier-1 + tier-2 are both silent on model existence — never fabricates a card for an…
staff-data-sci
Personas are Opus-only. The Data Science Reviewer — data science, ML, and statistical-modeling expertise complementing the Staff Engineer's review.
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…