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/josstei/maestro-orchestrate/ml_engineergit clone --depth 1 https://github.com/josstei/maestro-orchestrateWhat 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 | $0.00070 | $0.00198 |
| Opus 5 | $0.00035 | $0.00099 |
| Sonnet 5 | $0.00014 | $0.00040 |
| Haiku 4.5 | $0.00007 | $0.00020 |
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 3d 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
Agent methodology loaded via MCP tool get_agent. Call get_agent(agents: ["ml-engineer"]) to read the full methodology at delegation time.
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.
- 3d ago First seen · 24 lines · 70 tokens per session scan A bbd04b3fb9c4
ml_engineer is an agent published in the GitHub repository josstei/maestro-orchestrate (459 stars, last pushed 26d ago), licensed Apache-2.0. It adds 70 tokens to every session and 198 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
prompt-template-system
Agent "prompt-template-system" from bl1nk-bot/bl1nk-agents-manager, covering task, context injection rules, การใช้ context manager, สร้าง context and สร้าง prompt.
ai-ml-engineer
Builds, trains, and optimizes machine learning models and AI tools — model selection, prompts, evaluation, and integration.
ai-product-strategist
Strategy for AI-heavy products. Picks the right bets — model-vs-prompt architecture, build-vs-buy on models, data-moat assessment, commoditization risk, capability-vs-feature framing. Authors AI-product strategy docs distinct from standard product-strategist.
ai-rollback-strategist
Designs the fallback + rollback architecture for AI products. When the model fails (quality drop, cost spike, safety event, vendor outage), what does the user see and how does the system recover. Without this, AI products have brittle launches.
mlops-pm
Authors the model deployment, monitoring, drift detection, and incident-response plan. PM-side counterpart to engineering's mlops-reviewer. Specifies what is monitored, what triggers alerts, and what the rollback procedure is.
ai-engineer
Agent "ai-engineer" from frank-luongt/faos-skills-marketplace, covering 🤖 ai engineer: huyen chip, identity and communication style.