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 soba-labs/langchain-agent-skills --skill langsmith-deploymentgit clone --depth 1 https://github.com/soba-labs/langchain-agent-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/soba-labs/langchain-agent-skills/langsmith-deployment)<a href="https://agentmods.dev/skills/soba-labs/langchain-agent-skills/langsmith-deployment"><img src="https://agentmods.dev/badge/skills/soba-labs/langchain-agent-skills/langsmith-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/soba-labs/langchain-agent-skills/langsmith-deployment"><img src="https://agentmods.dev/badge/skills/soba-labs/langchain-agent-skills/langsmith-deployment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01511 |
| Opus 5 | $0.00044 | $0.00756 |
| Sonnet 5 | $0.00018 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
langsmith-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 11d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LangSmith Deployment
Use this skill to deploy, revise, monitor, and troubleshoot LangGraph-based agents in LangSmith Deployment.
Use This Skill When
- You need to deploy a new agent to LangSmith Cloud.
- You need to create a new deployment revision from Git changes or env changes.
- You need rollback guidance for a failing revision.
- You need to choose deployment model: Cloud, Hybrid/Self-hosted with control plane, or Standalone server.
- You need CI/CD automation using LangSmith Deployment control-plane APIs.
- You need monitoring and alert setup aligned with current LangSmith alert model.
- You need
langgraph.jsonvalidation and deployment compatibility checks.
Deployment Model Selection
| Model | Use when | Build/Source | Operates infra |
|---|---|---|---|
| Cloud | Fastest managed production path | GitHub repo via control plane | LangSmith |
| Hybrid/Self-hosted with control plane | You need private data plane + centralized deployment UI/API | Container image + control plane | You |
| Standalone server | You want direct Agent Server hosting without control plane | Containerized server | You |
Core Workflow
- Validate local deployment config.
- Choose deployment model and endpoint strategy.
- Create deployment or revision.
- Configure environment variables and secrets correctly.
- Configure monitoring and alerts.
- Verify runtime behavior and keep rollback path ready.
Script-First Commands
1) Validate langgraph.json
uv run python skills/langsmith-deployment/scripts/validate_deployment.py --config langgraph.json --target cloud
2) Create a Cloud deployment (US default)
uv run python skills/langsmith-deployment/scripts/deploy_to_langsmith.py \
--name "my-agent-prod" \
--owner my-org \
--repo my-agent-repo \
--branch main \
--config langgraph.json
3) Create a Cloud deployment (EU)
uv run python skills/langsmith-deployment/scripts/deploy_to_langsmith.py \
--name "my-agent-prod" \
--owner my-org \
--repo my-agent-repo \
--region eu
What ships with it
15 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.
- assets/templates/.env.example 880 B
- assets/templates/github-actions-deploy.yml 1.2 KB
- assets/templates/kubernetes-deployment.yaml 2.4 KB
- assets/templates/langgraph-cloud.json 113 B
- references/cicd-integration.md 4.6 KB
- references/deployment-guide.md 4.0 KB
- references/environment-management.md 3.7 KB
- references/monitoring-alerts.md 2.6 KB
- references/scaling-configuration.md 3.8 KB
- references/troubleshooting-deployment.md 4.2 KB
- scripts/deploy_to_langsmith.py 13 KB runs code
- scripts/deploy_to_langsmith.ts 12 KB runs code
- scripts/rollback_deployment.py 10 KB runs code
- scripts/setup_monitoring.py 8.9 KB runs code
- scripts/validate_deployment.py 12 KB runs code
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.
- 11d ago First seen · 164 lines · 88 tokens per session scan A f3735d17cf6a
langsmith-deployment is a skill published in the GitHub repository soba-labs/langchain-agent-skills (106 stars, last pushed 24d ago), licensed MIT. It adds 88 tokens to every session and 1,511 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…