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 agents-inc/skills --skill ai-infrastructure-replicategit clone --depth 1 https://github.com/agents-inc/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/agents-inc/skills/ai-infrastructure-replicate)<a href="https://agentmods.dev/skills/agents-inc/skills/ai-infrastructure-replicate"><img src="https://agentmods.dev/badge/skills/agents-inc/skills/ai-infrastructure-replicate.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Anti-Refusal · line 505 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 498 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00039 | $0.04591 |
| Opus 5 | $0.00019 | $0.02295 |
| Sonnet 5 | $0.00008 | $0.00918 |
| Haiku 4.5 | $0.00004 | $0.00459 |
Grade A, and why
ai-infrastructure-replicate 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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replicate SDK Patterns
Quick Guide: Use the
replicatenpm package to run open-source ML models on serverless GPUs. Usereplicate.run()for synchronous execution that returns output directly,replicate.stream()for SSE-based streaming, orreplicate.predictions.create()for async background jobs with webhook notifications. Models are referenced asowner/model(uses latest version) orowner/model:version(pinned). File outputs areFileOutputobjects implementingReadableStream. Cold starts are expected for infrequently-used models -- use deployments withmin_instancesto keep models warm.
<critical_requirements>
CRITICAL: Before Using This Skill
All code must follow project conventions in CLAUDE.md (kebab-case, named exports, import ordering,
import type, named constants)
(You MUST never hardcode API tokens -- always use environment variables via process.env.REPLICATE_API_TOKEN)
(You MUST handle FileOutput objects for models that return files -- do not assume outputs are plain strings or URLs)
(You MUST validate webhooks using validateWebhook() from the replicate package -- never trust unverified webhook payloads)
(You MUST account for cold starts when running infrequently-used models -- use deployments for latency-sensitive applications)
(You MUST specify model versions (owner/model:version) in production to ensure reproducible results -- unversioned references use the latest, which can change)
</critical_requirements>
Auto-detection: Replicate, replicate, replicate.run, replicate.stream, replicate.predictions, replicate.deployments, replicate.trainings, replicate.models, FileOutput, validateWebhook, REPLICATE_API_TOKEN, serverless GPU, cold start, webhook_events_filter
When to use:
- Running open-source ML models (Llama, Stable Diffusion, Whisper, etc.) without managing GPU infrastructure
- Generating images, transcribing audio, running LLMs, or any ML inference via API
- Streaming LLM output in real-time with server-sent events
- Processing predictions asynchronously with webhook notifications
- Fine-tuning models with custom training data
- Running models on dedicated hardware with custom scaling via deployments
What ships with it
5 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.
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 First seen · 532 lines · 39 tokens per session scan A a4338c01cb13
ai-infrastructure-replicate is a skill published in the GitHub repository agents-inc/skills (24 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 4,591 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 2026-08-30.
Other skills, from other repositories
typescript-strict
Use this skill when writing or reviewing TypeScript code with strict mode in WrongStack. Triggers: user mentions "TypeScript", "strict", "type error", "type safety", "narrowing", "branded type", "discriminated union", "noUncheckedIndexedAccess".
node-modern
Use this skill when writing, reviewing, or refactoring Node.js >= 22 TypeScript code in WrongStack. Triggers: ESM imports, fetch usage, AbortSignal, node: protocol, Web Streams, or any async patterns.
pytorch-lightning
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
date-threshold-arithmetic
Date comparisons at thresholds fail due to fractional days.
ts-debug
TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".
security-best-practices
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not…