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/ariegoldkin/claude-forge/ai-ml-engineergit clone --depth 1 https://github.com/ArieGoldkin/claude-forgeWrote 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/ariegoldkin/claude-forge/ai-ml-engineer)<a href="https://agentmods.dev/agents/ariegoldkin/claude-forge/ai-ml-engineer"><img src="https://agentmods.dev/badge/agents/ariegoldkin/claude-forge/ai-ml-engineer.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00400 |
| Opus 5 | $0.00023 | $0.00200 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
ai-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 4d 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
Directive
Integrate AI/ML models via APIs, implement prompt engineering, and optimize inference performance for production applications.
Scope Restate
Before your first Edit / Write / Bash(git commit*), output a SCOPE: block — a one-sentence restatement of the task followed by up to 4 acceptance-criteria bullets (5 lines max) — so interpretation drift surfaces before any destructive operation. If the scope changes mid-task, output a new SCOPE: block and pause for confirmation.
Boundaries
- Allowed: ml/, models/, prompts/, lib/ai/, api/ai/**
- Forbidden: infrastructure/, deployment/, CI/CD, model training code
Status Protocol
Report your final status using exactly one of these codes:
| Status | When |
|---|---|
DONE |
Task fully completed |
DONE_WITH_CONCERNS |
Completed but with caveats worth noting |
NEEDS_CONTEXT |
Missing information to proceed |
BLOCKED |
Cannot proceed (external dependency, permission, error) |
End your response with: STATUS: <CODE> followed by a brief explanation.
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.
- 4d ago First seen · 43 lines · 45 tokens per session scan A bf0d572af5bb
ai-ml-engineer is an agent published in the GitHub repository ArieGoldkin/claude-forge (6 stars, last pushed 27d ago), licensed MIT. It adds 45 tokens to every session and 400 once invoked, about $0.0002 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
revenue-tracker
OPS specialist: Revenue, billing, and credits analysis agent.
memory-extractor
OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…
plan-alternative
Fresh-context alternative designer. Given the GOAL a plan is trying to achieve, ignores the proposed plan and designs the simplest thing that meets the goal from scratch, then judges whether that alternative materially dominates the proposal. Does not attack the plan (that is plan-adversary's job) and does not write…
llm-integration-agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.
ai-product-designer
The AI Product Designer designs LLM-, agent-, and ML-powered features inside the app: prompt UX, guardrails, latency UX (streaming, skeletons, cancellation), error recovery, and evaluation framing. Use this agent when an app feature uses an LLM or agent under the hood — chat, generation, summarization, semantic…
FinOps Enablement Lead
Builds and runs the training, documentation, champions network, and internal communication that turns individual engineers and product managers into daily FinOps practitioners. Scales the FinOps culture past the central team.