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 joelbrilliant/agentic-delivery-skills --skill sandbox-to-production-gatesgit clone --depth 1 https://github.com/joelbrilliant/agentic-delivery-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/joelbrilliant/agentic-delivery-skills/sandbox-to-production-gates)<a href="https://agentmods.dev/skills/joelbrilliant/agentic-delivery-skills/sandbox-to-production-gates"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/sandbox-to-production-gates/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/joelbrilliant/agentic-delivery-skills/sandbox-to-production-gates"><img src="https://agentmods.dev/badge/skills/joelbrilliant/agentic-delivery-skills/sandbox-to-production-gates.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 | $0.00049 | $0.00679 |
| Opus 5 | $0.00024 | $0.00340 |
| Sonnet 5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
sandbox-to-production-gates 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 12d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandbox to Production Gates
Overview
Use this skill when an agent wants to move work from local or sandbox into production.
The goal is simple: prove that the reviewed source, built artefact, deployed service, and live runtime are the same thing.
Green tests are not a deployment. A restart is not a deployment. A deployed bundle without smoke evidence is not a deployment.
When to Use
- Promoting sandbox work to production.
- Restarting services after config or code changes.
- Verifying a deployed UI/API after build.
- Checking whether production is running the expected commit.
- Preparing rollback before risky changes.
- Reporting production status to a user.
Promotion Gates
Gate 1: Source truth
Capture:
- repo path;
- branch;
- commit SHA;
- dirty state;
- reviewed diff surface;
- exact files intentionally included.
If there is unrelated dirty work, do not stage it. Isolate the promotion.
Gate 2: Build truth
Run the real build command for the promoted surface.
Capture:
- command;
- exit code;
- artefact path or bundle name;
- build timestamp or hash when available.
Do not claim a build passed because a dev server still runs.
Gate 3: Service truth
Identify the actual runtime service:
- service name;
- port;
- process ID;
- environment file;
- working directory;
- last restart time.
Restart only the intended service. Never restart a neighbouring prod service by matching a vague process name.
Gate 4: Runtime truth
Smoke the live runtime, not localhost in the wrong mode.
Check:
- health endpoint;
- authenticated endpoint if auth exists;
- gateway/worker connectivity if relevant;
- static asset or API version;
- key user workflow;
- logs after startup.
If a public CDN or proxy blocks automation, smoke the backend with the correct Host header and say that is what you did.
Gate 5: Rollback truth
Before promotion, know the rollback:
- previous commit;
- previous build artefact if retained;
- command to restart old version;
- config backup location;
- data migration reversibility.
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.
- 12d ago First seen · 126 lines · 49 tokens per session scan A 3770e1a735e7
sandbox-to-production-gates is a skill published in the GitHub repository joelbrilliant/agentic-delivery-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 679 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 2026-08-31.
Other skills, from other repositories
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
doca-hardware-safety
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe…