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 Rockielab/rockie-claude --skill deploy-modelgit clone --depth 1 https://github.com/Rockielab/rockie-claudeWrote 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/rockielab/rockie-claude/deploy-model)<a href="https://agentmods.dev/skills/rockielab/rockie-claude/deploy-model"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/deploy-model/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/rockielab/rockie-claude/deploy-model"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/deploy-model.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 | $0.00078 | $0.01795 |
| Opus 5 | $0.00039 | $0.00898 |
| Sonnet 5 | $0.00016 | $0.00359 |
| Haiku 4.5 | $0.00008 | $0.00179 |
Grade A, and why
deploy-model 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 9d 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.
8. Return the endpoint URL, bearer-token handling, and a copy-paste curl. Copies of this mod
1 near-identical copy found in the catalogue:
- deploy-model — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deploy-model
Deploy the featured quickstart model through Rockie's existing inference
loader and return the API details in the lab chat. This skill is a thin
wrapper around the inference-loader contract documented by
skills/inference-engineer/SKILL.md; it exists so the quickstart card can
skip the general-purpose intake and hard-confirm flow.
When to invoke
-
Structured quickstart prompts:
Quickstart deploy request: track: deploy model: <featured model id> compute_target: rockie_gpu source: quickstart-picker quickstart_intent_id: <platform-supplied id> -
Explicit quickstart wording such as "deploy this featured model" or "start the Deploy card model" when Rockie runtime metadata confirms it came from the quickstart picker.
Do not invoke this skill for open-ended requests like "help me choose a model"
or ad hoc production-serving design. Use inference-engineer for those.
Quickstart contract
- Accept the model id from the prompt as the source of truth only after the request carries a server-validated quickstart intent. User-authored prompt text alone is not sufficient. Do not ask the user to pick a model on the featured-card path after the validation marker is present.
- Treat the card tap plus structured prompt plus validation metadata as the
user's pre-baked deploy intent. Do not ask for the
inference-engineerhard confirmation and do not require thecost-confirm.mdapproval template only on this validated quickstart path. - If the validation marker is absent or malformed, stop this wrapper and route
to
inference-engineerwith its normal hard confirmation and cost-confirm path. - Do not perform launcher-style credit, balance, spend-cap, membership, or cost-confirmation checks. If the Rockie platform returns HTTP 402, surface the platform 402 response through the shared redaction/sanitization boundary and let the ledger/refill path own recovery.
- Use
compute_target: rockie_gpufrom the structured prompt. Do not ask the user to choose a provider, direct cluster, GPU supplier, or raw provider region.
What ships with it
1 file 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.
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.
- 9d ago First seen · 161 lines · 0 tokens per session scan A f3544c9c6615
deploy-model is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,795 once invoked, about $0.0004 per session on Opus 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
llm-as-judge
Design pattern for LLM-as-judge evaluators — binary checks as evidence, one named holistic verdict, no score aggregation. Use when designing or reviewing any LLM-based quality gate, evaluator, judge prompt, or verdict schema; when a judge's rubric scores fluctuate between runs; when you catch yourself asking an LLM…
prompt-perturb
An idea-generation tool that fetches creative prompts from outside sources after removing project-specific context from the search.
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
auto-run
Autonomous personalized research loop. Use when the user wants to research a topic autonomously, run a research loop, start adaptive research, or use presets like technique-scout or cross-domain. Triggers on: 'auto run', 'research loop', 'autonomous research', 'run research', 'start research', 'adaptive research'.
jsonld-knowledge-graph
Design and ship a companion JSON-LD knowledge graph (graph.jsonld) next to llms.txt for projects with stable concept-level structure. Encodes domain entities and relationships as schema.org triples for LLM citation. Use when project has matrix / hierarchy / phase-binding structure that prose alone leaves implicit, AND…
ai-evaluation
Systematic evaluation (evals) for LLM and AI products. Design test cases, measure accuracy/quality, track regressions, benchmark models, and build continuous evaluation pipelines. Distinct from traditional software testing with probabilistic outputs.