modify-model

A Revit model editing command for Autodesk Revit, software used to create digital building models. It finds selected or matching elements and changes or removes them.

In plain words
What is it for?
Selecting elements, finding them by category or other filters, changing parameters, and deleting elements after confirmation.
Why use it?
It reduces the risk of editing the wrong model elements by identifying targets and showing changes before destructive actions.

Command

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/demolinator/revit-mcp-plugin/modify-model
Clone the repo
git clone --depth 1 https://github.com/Demolinator/revit-mcp-plugin
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00012 $0.00402
Opus 5 $0.00006 $0.00201
Sonnet 5 $0.00002 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 2d ago against content hash 78d078332869, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

modify-model 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 2d 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.

revit-bim/commands/modify-model.md · 39 lines

What it actually says

Modify, delete, or update elements in the Revit model based on user instructions.

Determine Action

Based on $ARGUMENTS:

"delete" / "remove":

  1. Identify elements to delete — by selection (get_selected_elements), by filter (ai_element_filter), or by IDs
  2. Confirm with the user before deleting (show count and types)
  3. Call delete_elements with the element IDs
  4. Report deleted count and any cascaded deletions (hosted elements)

"modify" / "change" / "set" / "update":

  1. Identify the target element(s) — by selection, filter, or ID
  2. Identify which parameters to change and new values
  3. Call modify_element for each element
  4. Report old and new values for confirmation

"select" / "what's selected":

  1. Call get_selected_elements
  2. Present: ID, Category, Type, Level, Key Parameters

"find" / "filter":

  1. Call ai_element_filter with appropriate category and criteria
  2. Present matching elements in a table

Rules

  • Always confirm destructive operations (delete) before executing
  • Report cascaded deletions (e.g., deleting a wall also removes hosted doors)
  • When modifying, show old values alongside new values
  • If element IDs are needed but not provided, help the user find them via selection or filtering
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. 2d ago First seen · 39 lines · 12 tokens per session scan A 78d078332869

Subscribe to this mod's changes

modify-model is a command published in the GitHub repository Demolinator/revit-mcp-plugin (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 402 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.