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-workload-apigit 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-workload-api)<a href="https://agentmods.dev/skills/datarobot-oss/datarobot-agent-skills/datarobot-workload-api"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/datarobot-workload-api/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-workload-api"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/datarobot-workload-api.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 Tool Misuse · line 284 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00142 | $0.05047 |
| Opus 5.5 | $0.00057 | $0.02019 |
| Sonnet 5.5 | $0.00028 | $0.01009 |
| Haiku 4.5 | $0.00014 | $0.00505 |
Grade A, and why
datarobot-workload-api scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`DATAROBOT_ENDPOINT` (must end `/api/v2`) and `DATAROBOT_API_TOKEN`: required as env vars only for raw REST (`scripts/`, `httpx`/`curl`) or CI — these bypass CLI auth. Header: `Authorization: Bearer ${DATAROBOT_API_TOKEN How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataRobot Workload API
Runs containers as managed, autoscalable DataRobot services. Four jobs — pick by intent:
- Create / configure / scale — deploy a container; change replicas, resources, autoscaling, bundle; inject credentials
- Diagnose — workload stuck, errored, or crash-looping
- Observe — logs, traces, metrics, service stats for a running workload
- Artifact lifecycle — iterate drafts, build images, lock for production, roll out new versions
Prerequisites
Auth: like gh. dr auth login (or existing .env/~/.config/datarobot/drconfig.yaml) persists credentials — no per-run env vars needed. Verify with dr auth check. On failure, run datarobot-setup.
Keep the CLI current (like datarobot-agent-assist): dr self update --force. Never gate on a pinned version. If a subcommand still errors unknown command after update, use the raw-REST fallback below.
DATAROBOT_ENDPOINT (must end /api/v2) and DATAROBOT_API_TOKEN: required as env vars only for raw REST (scripts/, httpx/curl) or CI — these bypass CLI auth. Header: Authorization: Bearer ${DATAROBOT_API_TOKEN}. Not in the datarobot Python SDK — call REST directly.
Transport: examples use Python httpx (pip install httpx); curl or the pulumi-datarobot provider work too.
Bundled scripts
Python in scripts/. Each uses httpx, reads DATAROBOT_ENDPOINT + DATAROBOT_API_TOKEN:
wait_for_running.py <workload_id>— poll untilrunning; exit 2 on terminal failure, 3 on timeoutdiagnose_workload.py <workload_id>— run the 5-step debug flow, print a diagnosis (--jsonfor machine output)wait_for_build.py <artifact_id> <build_id>— poll a server-side image build; dumps last 2KB of logs onFAILEDwait_for_replacement.py <workload_id>— poll a rolling replacement; handles the 404-when-cleared casecheck_limits.py— print effective org scaling limits via/account/info/
Deeper docs in references/
In references/:
status-vocabulary.md— status enums and transitionscommon-error-patterns.md— CrashLoopBackOff / ImagePullBackOff / OOMKilled / probe / exec-formatschema-reference.md— schemas, credential-type→key maps, spec quirkslifecycle-flows.md— draft→lock→prod rules, replacement preconditions, redeploy matrixcode-to-workload.md— deploy from source:drCLI,codeRef, Execution Environmentsdeclarative-cli-deploy.md—dr workload config/up: the one-command path from a project directory, and when the granular verbs are the better choice;.datarobot.yaml,promote,--sync-env,--spec-file,delete --purgecli-command-map.md— everydr workload/dr artifactverb → REST route, incl.diagnose,events,settings,logsfiltersweb-uis-behind-the-edge.md— web UI through the endpoint: prefix, auth gate, CSRF, WebSockets
What ships with it
13 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.
- references/cli-command-map.md 4.1 KB
- references/code-to-workload.md 15 KB
- references/common-error-patterns.md 6.9 KB
- references/declarative-cli-deploy.md 12 KB
- references/lifecycle-flows.md 7.4 KB
- references/schema-reference.md 5.8 KB
- references/status-vocabulary.md 4.1 KB
- references/web-uis-behind-the-edge.md 14 KB
- scripts/check_limits.py 2.8 KB runs code
- scripts/diagnose_workload.py 8.7 KB runs code
- scripts/wait_for_build.py 4.1 KB runs code
- scripts/wait_for_replacement.py 4.0 KB runs code
- scripts/wait_for_running.py 3.0 KB runs code
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.
- 11d ago Changed · +2 lines f5fa9591d02d
- 18d ago Changed · +3 lines 4b057781c0c5
- 1mo ago Changed · +1 lines · -10 tokens per session 023285dae2f5
- 1mo ago Changed · +2 lines d09f3c1913ad
- 1mo ago First seen · 342 lines · 152 tokens per session scan A a67aab36bb72
datarobot-workload-api is a skill published in the GitHub repository datarobot-oss/datarobot-agent-skills (32 stars, last pushed 4d ago), licensed Apache-2.0. It adds 142 tokens to every session and 5,047 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
offensive-container-escape
Container escape and breakout techniques targeting Docker, containerd, and Podman runtimes. Covers privileged container breakout via host filesystem mount and nsenter, Docker socket abuse through /var/run/docker.sock, Linux capability exploitation including CAPSYSADMIN, CAPSYSPTRACE, and CAPNETADMIN, cgroup v1…
agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
kubernetes
Use when deploying to or debugging Kubernetes. Covers workload configuration, resource requests and limits, probes, rollout strategy, networking, and the failure modes that produce CrashLoopBackOff and OOMKilled. Trigger on "pod keeps restarting", "pod stuck in crashloopbackoff", "container got oomkilled". Do not use…
upstash-box-remote-work
Do work in an Upstash Box, a sandboxed cloud container driven through the remote Upstash MCP server (mcp.upstash.com), instead of on the local machine. Use when the user asks to run, build, test, clone, or edit something remotely, in a sandbox, in the cloud, or in a box, when the deliverable is a pull request, a…
apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
apify-actorization
Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker images that accept well-defined JSON input, perform an action, and optionally produce structured JSON output.