metashape-reconstruction

metashape-reconstruction is a skill for Claude Code from jenkinsm13/metashape-mcp. It costs 59 tokens per session (1,658 once invoked), scanned A, original, MIT.

A workflow guide for creating detailed 3D reconstruction products in Agisoft Metashape through an MCP server, a connection that lets an AI assistant operate software tools. It covers processing steps after photos have been aligned.

In plain words
What is it for?
Use it to build depth maps, dense point clouds, meshes, textures, digital elevation models, and orthomosaics from aligned cameras.
Why use it?
It helps keep reconstruction steps in the correct order and use suitable processing settings while accounting for operations that may take hours or days.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the metashape-mcp plugin — 12 skills, 8 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to build depth maps, dense point clouds, meshes, textures, digital elevation models, and orthomosaics from aligned cameras.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jenkinsm13/metashape-mcp/metashape-reconstruction
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.

Any agent
npx skills add jenkinsm13/metashape-mcp --skill metashape-reconstruction
Clone the repo
git clone --depth 1 https://github.com/jenkinsm13/metashape-mcp

Made for: Claude Code.

Or install metashape-mcp, the plugin that ships this one along with the rest of its 12 skills, 8 agents, 2 hooks, 1 MCP server.

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 metashape-reconstruction

README.md
[![agentmods](https://agentmods.dev/badge/skills/jenkinsm13/metashape-mcp/metashape-reconstruction/github.svg)](https://agentmods.dev/skills/jenkinsm13/metashape-mcp/metashape-reconstruction)
Your own site
<a href="https://agentmods.dev/skills/jenkinsm13/metashape-mcp/metashape-reconstruction"><img src="https://agentmods.dev/badge/skills/jenkinsm13/metashape-mcp/metashape-reconstruction/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 metashape-reconstruction

Your own site · 80×15
<a href="https://agentmods.dev/skills/jenkinsm13/metashape-mcp/metashape-reconstruction"><img src="https://agentmods.dev/badge/skills/jenkinsm13/metashape-mcp/metashape-reconstruction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,658 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 $0.00059 $0.01658
Opus 5 $0.00030 $0.00829
Sonnet 5 $0.00012 $0.00332
Haiku 4.5 $0.00006 $0.00166

Measured 12d ago against content hash 5f80028ba36a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

metashape-reconstruction 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 12d 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.

skills/metashape-reconstruction/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metashape Dense Reconstruction via MCP

Overview

Build dense products from aligned cameras in Metashape using MCP tools. This covers everything AFTER alignment: depth maps, dense point cloud, mesh, texture, DEM, and orthomosaic. All MCP tool calls block until complete — no polling, no timeouts.

When to Use

  • Building depth maps, point cloud, mesh, or texture in Metashape
  • Generating DEM or orthomosaic survey products
  • Any processing step after photo alignment is complete

Golden Rules

  1. CPU OFF for all dense operations. set_gpu_config(cpu_enable=False) before depth maps, point cloud, meshing, texturing, DEM, orthomosaic. CPU slows GPU operations. CPU is ONLY for alignment (match_photos, align_cameras).
  2. NEVER write pipeline scripts. Call each MCP tool individually, check the result, adapt. This is an AGENT workflow.
  3. No timeouts. Dense operations can take hours or days. MCP calls block until done.
  4. No polling. Don't call get_processing_status in a loop.
  5. Save after every step. The MCP tools auto-save, but verify with save_project() after major operations.
  6. Check prerequisites. Each step requires the previous step's output. Verify before proceeding.

Standard Dense Pipeline

Step 0: Verify alignment is complete

get_alignment_stats()
# Check: alignment_rate should be >95%
# Check: tie_point_count_valid should be reasonable

Step 1: GPU config — CPU OFF

set_gpu_config(cpu_enable=False)

Step 2: Build depth maps

build_depth_maps(
    downscale=2,          # 1=Ultra, 2=High, 4=Medium, 8=Low, 16=Lowest
    filter_mode="mild",   # mild for complex terrain, moderate default, aggressive for clean scenes
    reuse_depth=True      # Reuse existing depth maps for aligned cameras
)

Quality guide:

  • downscale=1 (Ultra): Final production, small projects. Very slow.
  • downscale=2 (High): Standard production quality. Good balance.
  • downscale=4 (Medium): Quick results, large projects, testing.

Read the full file on GitHub · 189 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. 12d ago First seen · 189 lines · 59 tokens per session scan A 5f80028ba36a

Subscribe to this mod's changes

metashape-reconstruction is a skill published in the GitHub repository jenkinsm13/metashape-mcp (34 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,658 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

i4h-workflow-train-rl

Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.

NVIDIA/skills · 38 tokens

godot-optimization

Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.

jame581/GodotPrompter · 28 tokens

cad-mesh-3dgs

Bridge CAD, Mesh, and 3DGS representations via the SLAT unified encode-decode framework. Covers mesh↔3DGS conversion, surface extraction, CAD reverse engineering, B-rep/parametric reconstruction, NL-driven assembly, TetSphere physics bridge, PBR material generation. Analyzes 40+ methods. Use when: converting mesh…

jaccen/Awesome-Gaussian-Skills · 140 tokens

3dgs-compression-deploy

3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment, hardware acceleration (Tensor Core/GEMM/FPGA/ASIC), training-free semantic compression. Covers 53+ methods across 6…

jaccen/Awesome-Gaussian-Skills · 145 tokens

3dgs-experiment-planner

Design rigorous experiments for 3DGS research papers. Recommends datasets, baselines, metrics, ablation matrices. Targets CVPR/ICCV/ECCV/SIGGRAPH/TVCG. Use when: designing experiments for a 3DGS paper, selecting datasets/baselines/metrics, planning ablation studies, addressing reviewer concerns on experiments…

jaccen/Awesome-Gaussian-Skills · 96 tokens

3dgs-visualizer

A chart-making tool for research on 3D Gaussian Splatting (3DGS), a technique for representing and rendering 3D scenes from images. It creates radar charts, comparison tables, and timelines for comparing research methods.

jaccen/Awesome-Gaussian-Skills · 84 tokens