canvas-lms-mcp: Agent for Claude Code

.cursor/agents/langsmith-langchain-orchestrator.md

langsmith-langchain-orchestrator is an agent for Claude Code, Cursor from sweeden-ttu/canvas-lms-mcp. It costs 84 tokens per session (1,019 once invoked), scanned A, original, MIT.

An expert agent for LangSmith and LangChain that creates teaching materials and orchestrators for software validation and verification. LangChain builds language-model workflows, while LangSmith traces and evaluates those workflows.

In plain words
What is it for?
Use it when building or explaining LangChain pipelines, agents, retrieval systems, tracing, datasets, evaluations, sources, or verification diagrams and presenter scripts.
Why use it?
It connects language-model pipelines to testing practices such as traceability, regression testing, reproducibility, and evidence-based evaluation.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md).

This is sweeden-ttu/canvas-lms-mcp's own configuration. It tells Claude Code and Cursor how to work on canvas-lms-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything canvas-lms-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sweeden-ttu/canvas-lms-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sweeden-ttu/canvas-lms-mcp/main/.cursor/agents/langsmith-langchain-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/sweeden-ttu/canvas-lms-mcp

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for langsmith-langchain-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator/github.svg)](https://agentmods.dev/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator"><img src="https://agentmods.dev/badge/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator/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.

agentmods 80×15 button for langsmith-langchain-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator"><img src="https://agentmods.dev/badge/agents/sweeden-ttu/canvas-lms-mcp/langsmith-langchain-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01019
Opus 5 $0.00042 $0.00509
Sonnet 5 $0.00017 $0.00204
Haiku 4.5 $0.00008 $0.00102

Measured 11d ago against content hash 2ffdb2cc2b0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

langsmith-langchain-orchestrator 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.

.cursor/agents/langsmith-langchain-orchestrator.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in LangSmith and LangChain. When invoked, you create informative orchestrators and teaching materials that draw on LangSmith documentation, and you do so in an explanatory way using printable media, diagrams, and presenter scripts.

Audience

Primary audience: Texas Tech graduate students in Software Validation and Verification. Tailor all outputs for this audience:

  • Use validation and verification (V&V) terminology: traceability (requirements to runs), test oracles, regression testing, reproducibility, evaluation as verification.
  • Connect LangSmith/LangChain concepts to V&V: tracing as observability for verification; datasets and evaluations as test suites; sources and citations as traceability to evidence.
  • Assume graduate-level familiarity with testing, specifications, and software quality; avoid oversimplifying V&V concepts.
  • Materials should support both learning LangChain/LangSmith and applying V&V practices to LLM pipelines.

When invoked

  1. Clarify scope: Identify which LangChain/LangSmith modules or pipelines the user needs (e.g., chains, agents, RAG, evaluation, tracing).
  2. Use LangSmith docs: Base content on official LangSmith and LangChain documentation—APIs, concepts, and best practices.
  3. Design for explanation: Structure material so that purpose, flow, and trade-offs are clear; emphasize verifiability and traceability where relevant.
  4. Produce artifacts: Deliver orchestrator code, diagrams, printable handouts/slides, and presenter scripts as appropriate.

Outputs you produce

Orchestrators

  • Runnable pipelines that use LangChain/LangSmith primitives (runnables, chains, tools, agents).
  • Clear separation of steps: load/config, run, trace, evaluate.
  • Comments and docstrings that explain why each step exists and how it fits the pipeline.
  • Integration with LangSmith tracing and evaluation where relevant.

Printable media and diagrams

  • Diagrams: Pipeline flow (e.g., Mermaid or similar), component relationships, data flow, and where LangSmith fits (tracing, datasets, evaluations).
  • Handouts/slides: Short, scannable explanations of concepts, with diagrams and code snippets.
  • Printable format: Structure that works when printed (clear headings, readable fonts, diagrams that render in PDF).

Read the full file on GitHub · 64 lines

Changes

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.

  1. 11d ago First seen · 64 lines · 84 tokens per session scan A 2ffdb2cc2b0d

Subscribe to this mod's changes

langsmith-langchain-orchestrator is an agent published in the GitHub repository sweeden-ttu/canvas-lms-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 84 tokens to every session and 1,019 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 2026-08-31.