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 skills/prevu-cloud/prevu/prevu-flowsnpx skills add prevu-cloud/prevu --skill prevu-flowsgit clone --depth 1 https://github.com/prevu-cloud/prevuWhat 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 | $0.00100 | $0.01213 |
| Opus 5 | $0.00050 | $0.00607 |
| Sonnet 5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
prevu-flows 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prevu - Workflow Flows
Two multi-step user-facing scenarios that wire the prevu CLI into a coherent loop. Each has its own playbook in references/. Load this skill when the user's intent is a workflow, not a single command. For command-level reference (every flag, every exit code), the prevu skill is the source.
Flow A - Mirror local dev to the user's phone (the AFK loop)
Read references/mirror-dev.md when the user wants to keep iterating with you while away from their laptop. Trigger phrases:
- "I'm heading out, can you keep working on this?"
- "Mirror this to Prevu / spin up a remote dev env"
- "I want to review changes on my phone tonight"
- "Set up so I can drive it from mobile"
- "Keep coding while I'm AFK"
The shape of the loop:
user (phone): "change X"
down
you: edit locally -> commit -> push
down
env: pulls -> dev server hot-reloads
down
user (phone): refreshes preview URL -> "no, do Y"
down ... repeat until accepted ...
Crucial: Prevu is the preview target, not the editing machine. Edits happen in the user's local checkout where their files, history, and secrets live. The env only sees what you push. Don't dual-edit.
Flow B - Share a WIP preview URL
Read references/share-preview.md when the user wants someone else (teammate, designer, PM, or themselves later from a different device) to see in-progress work without waiting for a deploy. Trigger phrases:
- "Show this to the backend team"
- "Send my designer a preview link"
- "I want a shareable URL for this branch"
- "Get this in front of "
The shape of the flow is shorter than mirror-dev: provision (or reuse) -> push the branch -> install + start dev server -> expose HTTPS -> hand back one URL. Once the URL is sent, you're done. No iterate loop unless the user comes back with feedback.
Decision tree - which flow?
| User said... | Use |
|---|---|
| "Going AFK / keep coding / drive from mobile" | Flow A (mirror-dev) |
| "Show / share / send" + a person or audience | Flow B (share-preview) |
| "Just create a Prevu env" with no further intent | The prevu skill - env create is enough |
| "Deploy" / "production" | Neither - Prevu is for preview environments before production |
What ships with it
2 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.
- 3d ago First seen · 97 lines · 0 tokens per session scan A 4eb08d22c04d
prevu-flows is a skill published in the GitHub repository prevu-cloud/prevu (11 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,213 once invoked, about $0.0005 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
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
doca-container-deployment
Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod manifests directory, YAML pod-spec drop, kubelet status / ENTRYPOINT logs / per-service liveness, smoke-before-bulk, and the layered…
amc-setup-calibration-stack
Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.
hyperpod-cluster-debugger
Diagnose and remediate cluster-wide HyperPod (EKS or Slurm) problems — creation / deployment failures (CloudFormation, EFA health check, lifecycle scripts, capacity), EKS access, node replacement, CloudFormation nested-stack errors, post-maintenance rollback state, dangling nodes, autoscaler conflicts. Includes…
hyperpod-nccl
Diagnose NCCL failures and adjacent training-pod failures on HyperPod GPU clusters (EKS or Slurm) — training hangs, AllReduce / collective-op timeouts, EFA or libfabric errors, rendezvous failures, EFA TCP fallback, /dev/shm or memlock issues, NCCL version mismatch across pods, container OOM / exit-137 / OOMKilled…
cloudbase-platform
CloudBase platform overview and routing guide. This skill should be used when users need high-level capability selection, platform concepts, console navigation, or cross-platform best practices before choosing a more specific implementation skill.