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 skills add datarobot-oss/datarobot-agent-skills --skill datarobot-agent-assistgit clone --depth 1 https://github.com/datarobot-oss/datarobot-agent-skillsWrote 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/skills/datarobot-oss/datarobot-agent-skills/datarobot-agent-assist)<a href="https://agentmods.dev/skills/datarobot-oss/datarobot-agent-skills/datarobot-agent-assist"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/datarobot-agent-assist/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/skills/datarobot-oss/datarobot-agent-skills/datarobot-agent-assist"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/datarobot-agent-assist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 146 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00182 | $0.04915 |
| Opus 5 | $0.00091 | $0.02457 |
| Sonnet 5 | $0.00036 | $0.00983 |
| Haiku 4.5 | $0.00018 | $0.00492 |
Grade A, and why
datarobot-agent-assist 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.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataRobot Agent Assist
This skill covers agent design, coding, battle-testing, and deployment with an optional dress-rehearsal simulation before any code is written.
A first message of 1–4 selects the corresponding category. If free text clearly maps to one category (e.g. "I want to build an agent" → Design), state the inference briefly and proceed. If ambiguous, ask which option applies — do not guess.
Workflow Discipline
Follow this skill sequentially. These rules apply to every phase — design, coding, deployment, and every referenced checklist.
- Section order — Complete each section and subsection in the order it appears in this file. Do not jump to a later section until the current one is finished.
- Reference files — When this skill says read and follow a file under
agent-assist-build/references/, read that file first, then execute every step in that file in order. Do not substitute a summary, shortcut, or a later menu for steps defined in the reference. - Explicit skips only — Skip a step only when this skill or the referenced file explicitly says to skip it (e.g. Pre-requisite Check when
<prerequisites_passed>is true, or Frontend Check whenfrontend.typeis already set). - No auto-advance — Completing one step (e.g. writing the spec, the user saying "move on", or a command succeeding) does not authorize skipping remaining steps. Proceed only when the current section or reference directs you to the next step.
- Menus and prompts — When a section presents a menu or asks a question, wait for the user's reply. Do not assume a default or proceed on your own.
- One design gate per turn — During design, do not combine prompts from different subsections in one message (e.g. do not ask about spec refinement and dress rehearsal in the same turn).
On Activation
Present the four options clearly:
Welcome! I help you design, code, battle-test, and deploy AI agents.
What would you like to do?
1. Design an AI agent → Describe your idea (optional dress rehearsal before coding)
2. Code an AI agent → Load and implement an existing agent_spec.md
3. Battle-test the agent → Run adversarial swarm simulation on an implemented agent
4. Deploy → Deploy an implemented agent to DataRobot
What ships with it
39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agent-assist-build/references/agent-spec-examples.md 4.1 KB
- agent-assist-build/references/agent-spec-schema.md 1.7 KB
- agent-assist-build/references/dependency-validation.md 1005 B
- agent-assist-build/references/dr-cli-setup.md 872 B
- agent-assist-build/references/dress-rehearsal.md 7.5 KB
- agent-assist-build/references/helper-scripts.md 5.1 KB
- agent-assist-build/references/llm-selection.md 3.5 KB
- agent-assist-build/references/pre-coding-checklist.md 13 KB
- agent-assist-build/references/pre-deployment-checklist.md 2.2 KB
- agent-assist-build/references/resume-design.md 6.8 KB
- agent-assist-build/references/tool-mapping.md 852 B
- agent-assist-build/references/workspace-resolution.md 6.1 KB
- agent-assist-build/scripts/check_codespace.py 8.1 KB runs code
- agent-assist-build/scripts/clone_template.py 7.4 KB runs code
- agent-assist-build/scripts/env_utils.py 3.9 KB runs code
- agent-assist-build/scripts/list_llm_models.py 19 KB runs code
- agent-assist-build/scripts/rehearsal.py 44 KB runs code
- agent-assist-build/scripts/select_framework.py 2.4 KB runs code
- agent-assist-build/scripts/setup_template.py 22 KB runs code
- agent-assist-build/scripts/write_rehearsal_report.py 12 KB runs code
- agent-assist-build/SKILL.md 18 KB
- agent-assist-simulate/prompts/evaluate-result.md 3.8 KB
- agent-assist-simulate/prompts/generate-attack.md 4.0 KB
- agent-assist-simulate/prompts/generate-behavior.md 3.9 KB
- agent-assist-simulate/prompts/generate-persistence.md 4.2 KB
- agent-assist-simulate/prompts/generate-tool-return.md 4.7 KB
- agent-assist-simulate/prompts/industry.md 13 KB
- agent-assist-simulate/prompts/run-scenario.md 2.8 KB
- agent-assist-simulate/scripts/artifacts.py 7.6 KB runs code
- agent-assist-simulate/scripts/gateway_worker.py 12 KB runs code
- agent-assist-simulate/scripts/native_convergence.py 13 KB runs code
- agent-assist-simulate/scripts/native_execution.py 16 KB runs code
- agent-assist-simulate/scripts/native_scenarios.py 11 KB runs code
- agent-assist-simulate/scripts/native_swarm.py 25 KB runs code
- agent-assist-simulate/scripts/prompt_inputs.py 3.9 KB runs code
- agent-assist-simulate/scripts/swarm_contracts.py 6.8 KB runs code
- agent-assist-simulate/scripts/tool_executor.py 3.8 KB runs code
- agent-assist-simulate/scripts/write_report.py 6.3 KB runs code
- agent-assist-simulate/SKILL.md 17 KB
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 Changed · -7 lines d50f2712daa4
- 13d ago First seen · 314 lines · 182 tokens per session scan A e7624df1dfcc
datarobot-agent-assist is a skill published in the GitHub repository datarobot-oss/datarobot-agent-skills (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 182 tokens to every session and 4,915 once invoked, about $0.0009 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 skills, from other repositories
upstash-vector-js
Work with the @upstash/vector TypeScript/JavaScript SDK, a serverless vector database for embeddings, similarity search, semantic search, and RAG (retrieval-augmented generation). Use when upserting, querying, fetching, ranging, or deleting vectors, upserting raw text against an index with a built-in embedding model…
fine-tuning
Use when considering fine-tuning a model. Covers when fine-tuning beats prompting or RAG, dataset construction, LoRA and full fine-tuning, evaluation, and the failure modes that waste the effort.
llm-cost-optimization
Use when an LLM feature costs too much. Covers prompt caching, context reduction, model routing, batching, output limits, and finding where the tokens actually go.
llm-evaluation
Use when measuring the quality of an LLM feature. Covers building an evaluation set, choosing metrics, LLM-as-judge and its pitfalls, regression testing prompts, and evaluating in production.
llm-integration
Use when integrating an LLM API into an application. Covers streaming, retries and rate limits, timeouts, caching, fallback across providers, and the production concerns that a tutorial integration ignores.
ml-pipeline
Use when building or operating a machine learning pipeline. Covers feature engineering, training reproducibility, train/serve skew, deployment, monitoring for drift, and retraining.