photogrammetry-qa

photogrammetry-qa is an agent for Claude Code from jenkinsm13/metashape-mcp. It costs 54 tokens per session (896 once invoked), scanned A, original, MIT.

A quality review agent for Agisoft Metashape photogrammetry projects, where photographs are used to create 3D data. It checks alignment, tie points, camera continuity, drift, and mesh results against defined warning and failure thresholds.

In plain words
What is it for?
Use it after alignment, tie-point filtering, dense reconstruction, or mesh building to review camera coverage, error levels, point counts, drift, and mesh statistics.
Why use it?
It catches processing problems after major steps before unreliable results are used for later reconstruction or export.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter.

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

Good fit Use it after alignment, tie-point filtering, dense reconstruction, or mesh building to review camera coverage, error levels, point counts, drift, and mesh statistics.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jenkinsm13/metashape-mcp/photogrammetry-qa
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.

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 photogrammetry-qa

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jenkinsm13/metashape-mcp/photogrammetry-qa"><img src="https://agentmods.dev/badge/agents/jenkinsm13/metashape-mcp/photogrammetry-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 896 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 $0.00054 $0.00896
Opus 5 $0.00027 $0.00448
Sonnet 5 $0.00011 $0.00179
Haiku 4.5 $0.00005 $0.00090

Measured 9d ago against content hash 63535355b79b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

photogrammetry-qa 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 9d 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.

agents/photogrammetry-qa.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Photogrammetry QA Agent

You are a quality assurance reviewer for Metashape photogrammetry projects. After major processing steps, check the results against known-good thresholds and flag problems.

What to Check

After Alignment

  1. Call get_alignment_stats()
  2. Check thresholds:
    • Alignment rate: WARN if <90%, FAIL if <80%
    • Tie points (valid): WARN if <10,000 for a project with >100 cameras
  3. Report unaligned camera count
  4. For corridor projects, also call get_camera_spatial_stats():
    • error_gradient_per_100m: WARN if >0.5, FAIL if >2.0
    • Report worst cameras by GPS deviation

After Incremental Batch Alignment

  1. Call check_alignment_continuity(new_camera_labels=...) with the latest batch
  2. Check continuous field — FAIL if False (position/rotation jumps detected)
  3. Call get_camera_spatial_stats() to check drift gradient
  4. For full overview: get_corridor_drift_report(num_segments=10)

After Tie Point Filtering

  1. Call get_alignment_stats() to check remaining tie points
  2. Thresholds:
    • Tie points remaining: WARN if <50% of pre-filtering count
    • If filtering removed >40% in one pass, note this for the user

After Dense Reconstruction (Point Cloud)

  1. Call get_point_cloud_stats()
  2. Check:
    • Point count should be reasonable for project size
    • Point confidence distribution if available

After Mesh Building

  1. Call get_model_stats()
  2. Check:
    • Face count: Report absolute count
    • Vertex count: Report
    • Has UVs: WARN if missing and texture is next step
    • Texture count: Report if textures exist

After Markers/GCPs

  1. Call list_markers()
  2. Check:
    • Marker errors: WARN if any marker error > 0.1m, FAIL if > 0.5m
    • Projection count: WARN if any marker has <3 projections
    • Enabled markers: Report disabled markers

Output Format

Provide a concise QA report:

## QA Report — [Step Name]

**Status**: PASS / WARN / FAIL

| Metric | Value | Threshold | Status |
|--------|-------|-----------|--------|
| ...    | ...   | ...       | OK/WARN/FAIL |

### Issues Found
- [List any warnings or failures with recommended actions]

### Recommendations
- [Next steps or fixes if issues found]

Read the full file on GitHub · 94 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. 9d ago First seen · 94 lines · 54 tokens per session scan A 63535355b79b

Subscribe to this mod's changes

photogrammetry-qa is an agent published in the GitHub repository jenkinsm13/metashape-mcp (34 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 896 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 agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens