create-adr

create-adr is a command for Claude Code from vishnu2kmohan/mcp-server-langgraph. It costs 21 tokens per session (1,983 once invoked), scanned A, original, MIT.

A command that creates an Architecture Decision Record, a document explaining an important technical choice and why it was made. It generates the record in two formats.

In plain words
What is it for?
Use it when documenting a new technical decision in the mcp-server-langgraph project. It asks for the decision title and category before creating the record.
Why use it?
It gives the project a repeatable way to record decisions about architecture, infrastructure, security, and related areas.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/vishnu2kmohan/mcp-server-langgraph/create-adr
Clone the repo
git clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraph

Made for: Claude Code.

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 create-adr

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/create-adr.svg)](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/create-adr)
Your own site
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/create-adr"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/create-adr.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.01983
Opus 5 $0.00010 $0.00992
Sonnet 5 $0.00004 $0.00397
Haiku 4.5 $0.00002 $0.00198

Measured 4d ago against content hash f918875114b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-adr 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 4d 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.

.claude/commands/create-adr.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Architecture Decision Record

You are tasked with creating a new Architecture Decision Record (ADR) for the mcp-server-langgraph project. This command automates ADR creation with intelligent auto-filling and dual format generation.

Project Context

Project: MCP Server LangGraph Version: 2.8.0 Technology Stack:

  • Python 3.10+ with LangGraph
  • Multi-provider LLM via LiteLLM (Anthropic, OpenAI, Google, Azure, AWS, Ollama)
  • Authentication: JWT + Keycloak SSO
  • Authorization: OpenFGA (Zanzibar-style RBAC)
  • Observability: OpenTelemetry + LangSmith
  • Session Storage: Redis + PostgreSQL
  • Deployment: Kubernetes, GKE, Cloud Run, Helm

Your Task

Step 1: Gather Information

Ask the user for the following information using the AskUserQuestion tool:

Question 1: What is the title of the ADR?

  • Header: "ADR Title"
  • Provide text input for the title
  • Example: "GraphQL API Design for Agent Interactions"

Question 2: What category does this ADR fall under?

  • Header: "Category"
  • Options:
    • Architecture: Core architectural patterns
    • Infrastructure: Deployment, scaling, infrastructure
    • Security: Authentication, authorization, secrets
    • Observability: Monitoring, logging, tracing
    • Testing: Testing strategies and patterns
    • Data: Data storage, caching, persistence
    • Integration: External service integration
    • Performance: Performance optimization, caching

Question 3 (Optional): Are there related ADRs? (comma-separated numbers, e.g., "1,3,15")

  • Header: "Related ADRs"
  • Allow text input for comma-separated ADR numbers

Step 2: Determine Next ADR Number

  1. Use Bash to find the highest numbered ADR:

    ls adr/adr-*.md | sed 's/.*adr-0*\([0-9]*\)-.*/\1/' | sort -n | tail -1
    
  2. Add 1 to get the next ADR number

  3. Format as 4-digit zero-padded number (e.g., 0040)

Step 3: Auto-Link Related ADRs

If the user didn't specify related ADRs, search for them automatically based on keywords in the title:

Read the full file on GitHub · 201 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. 4d ago First seen · 201 lines · 21 tokens per session scan A f918875114b8

Subscribe to this mod's changes

create-adr is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 11d ago), licensed MIT. It adds 21 tokens to every session and 1,983 once invoked, about $0.0001 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.