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 OrcaQubits/agentic-commerce-skills-plugins --skill nlweb-deploymentgit clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-pluginsWrote 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/orcaqubits/agentic-commerce-skills-plugins/nlweb-deployment)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-deployment"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-deployment/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/orcaqubits/agentic-commerce-skills-plugins/nlweb-deployment"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-deployment.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 | $0.00091 | $0.01984 |
| Opus 5.5 | $0.00036 | $0.00794 |
| Sonnet 5.5 | $0.00018 | $0.00397 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
nlweb-deployment 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 1mo 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NLWeb Deployment
Before writing code
Fetch live docs:
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/setup-azure.md for Azure App Service deployment.
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/setup-snowflake.md for Snowflake Container Services.
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/setup-cloudflare-autorag.md for Cloudflare Worker + AutoRAG.
- Fetch https://developers.cloudflare.com/ai-search/how-to/nlweb/ for Cloudflare's hosted NLWeb documentation.
- Inspect
deploy_azure_webapp.sh,setup.sh,startup_aiohttp.shin the live repo for current commands. - Web-search the latest release notes for breaking deployment changes.
Conceptual Architecture
Deployment Targets Supported
| Target | Notes | Setup doc |
|---|---|---|
| Azure App Service | Reference deployment; ships shell scripts | docs/setup-azure.md |
| Snowflake Container Services | NLWeb runs inside Snowflake compute, closest to data | docs/setup-snowflake.md |
| Cloudflare Worker + AutoRAG | Edge deployment; CF manages indexing | docs/setup-cloudflare-autorag.md |
| Docker | Bring-your-own host | Build from Dockerfile if shipped, else manual |
| Bare Python | systemd + venv on a VM | Use app-aiohttp.py directly |
| WordPress plugin | For WP sites | code/wordpress/nlweb/ |
Production Hardening Checklist
Before exposing /ask or /mcp to the internet:
- Set
mode: productioninconfig_webserver.yaml— disables query-string config overrides. - Lock down the
sites:allowlist inconfig_nlweb.yaml— only the sites you want public. - Disable
who_endpoint_enabledif you don't want federated traffic going tonlwm.azurewebsites.net. - Turn off unused retrieval backends in
config_retrieval.yaml(nlweb_west,shopify_mcpunless needed). - Configure OAuth if you need auth (see
nlweb-auth-multitenancy). - Set TLS at the edge (App Service, CF, ALB, etc.).
- Set rate limits — NLWeb itself has limited built-in protection; do it at the edge.
- Configure CORS if a browser client calls
/askdirectly. - Persist conversations to a real storage provider (
config_storage.yaml), not in-memory. - Configure observability — logs, /mcp/health checks, latency metrics.
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.
- 1mo ago First seen · 171 lines · 0 tokens per session scan A 274213d0bad0
nlweb-deployment is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (40 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,984 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
archestra-dev-investigate
Use when investigating Archestra bugs or incidents — staging issues, backend 50x errors, Drizzle failed queries, DB connection pressure, deploy regressions, or Kubernetes/runtime symptoms. Orientation only; defers the process to /investigate.
archestra-dev-resource-cleanup
Reclaim unused Archestra development worktrees, local branches, processes, and OrbStack Kubernetes resources while preserving the active Tilt stack and unfinished work.
devops-engineer
Becomes a senior DevOps engineer who designs and implements CI/CD pipelines, infrastructure as code, monitoring systems, and deployment strategies. Use when the user needs build pipelines, container orchestration, cloud infrastructure, deployment automation, or observability setup. Do NOT use when writing application…
arwp-evidence-ci
Add ARWP verification, regression contracts, evidence receipts, scheduled audits, and CI to a website repository. Use when asked to continuously check ARWP quality, prevent agent/search regressions, monitor public interfaces, generate evidence, or prove that an ARWP implementation remains consistent over time. Keep…
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
test-environments
Design environment strategy for testing across dev, CI, preview, staging, and production — Docker Compose test infrastructure, multi-stage Dockerfiles, seed-data lifecycle, per-PR preview environments, production parity, and external-dependency stubbing at the HTTP boundary. Use when: "set up test environment,"…