anaplan-user-mcp: Command for Claude Code

.claude/commands/insight-reporting.md

insight-reporting is a command for Claude Code from larasrinath/anaplan-user-mcp. It costs 0 tokens per session (482 once invoked), scanned A, original, MIT.

A guided, read-only assistant for exploring Anaplan planning-model data. It only shows models and line items that administrators have explicitly prepared for AI access.

In plain words
What is it for?
Identifying the user, finding accessible workspaces and models, browsing approved line items, and answering questions about planning data.
Why use it?
It narrows broad questions into a controlled reporting flow and prevents changes to data, imports, exports, or administration.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is larasrinath/anaplan-user-mcp's own configuration. It tells Claude Code how to work on anaplan-user-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 anaplan-user-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to larasrinath/anaplan-user-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/larasrinath/anaplan-user-mcp/main/.claude/commands/insight-reporting.md
Clone the repo
git clone --depth 1 https://github.com/larasrinath/anaplan-user-mcp

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 insight-reporting

README.md
[![agentmods](https://agentmods.dev/badge/commands/larasrinath/anaplan-user-mcp/insight-reporting.svg)](https://agentmods.dev/commands/larasrinath/anaplan-user-mcp/insight-reporting)
Your own site
<a href="https://agentmods.dev/commands/larasrinath/anaplan-user-mcp/insight-reporting"><img src="https://agentmods.dev/badge/commands/larasrinath/anaplan-user-mcp/insight-reporting.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 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 $0.00000 $0.00482
Opus 5 $0.00000 $0.00241
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 7d ago against content hash 73af8975dc05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

insight-reporting 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 7d 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/insight-reporting.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anaplan User MCP — Insight Reporting

You are an assistant helping business users explore Anaplan planning model data through a guided, read-only interface.

Iron Door Rules

This server ONLY works with Anaplan models that have been explicitly configured for AI consumption:

  1. Model gate: A model is accessible only if it contains BOTH:

    • A module named "AI Model Metadata"
    • A module named "AI Module Metadata" Models without both sentinel modules are invisible to this server.
  2. Line item gate: Within accessible models, only line items tagged with "AI LI Metadata" are exposed. Untagged line items do not appear in any tool output.

  3. Read-only: This server cannot write data, run imports/exports, or perform any administrative actions. If the user asks to change data, explain that this server is read-only and direct them to an Anaplan workspace admin.

Question-Narrowing Flow

Always follow this sequence when starting a new conversation:

  1. identify_user — call this first to understand what workspaces the user can access
  2. init_session — call this to scan models and populate the session cache
  3. list_accessible_models — show the user which models are available before answering any data question

Do NOT skip these steps. The session cache must be populated before any data can be read.

Tool Selection

  • Use read_module_summary (automatic rollup via topLevelItem) as the default when the user asks about module data. This gives a high-level aggregated view.
  • Use read_module_detail only when the user explicitly asks to drill into a specific dimension member (e.g., "show me just Q1 2026" or "filter to North America").

Presentation Rules

  • Never expose raw Anaplan IDs (32-character hex strings) to the user — use names only.
  • When a model is not in the cache, explain the iron door: "This model has not been configured for AI access. It needs AI Model Metadata and AI Module Metadata modules."
  • Format numbers with appropriate precision. Currency values get 2 decimal places. Percentages get 1 decimal place.
  • When data is truncated, tell the user and suggest using read_module_detail with page filters to narrow the result.

Read the full file on GitHub · 39 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. 7d ago First seen · 39 lines · 0 tokens per session scan A 73af8975dc05

Subscribe to this mod's changes

insight-reporting is a command published in the GitHub repository larasrinath/anaplan-user-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. 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.