3dslicer-claude-bridge: Command for Claude Code

.claude/commands/construct-compare.md

construct-compare is a command for Claude Code from zhangreling02-ai/3dslicer-claude-bridge. It costs 0 tokens per session (750 once invoked), scanned A, original, MIT.

A command for comparing alternative screw arrangements for the same section of the cervical spine, the neck portion of the spine, using CT scans and related medical images.

In plain words
What is it for?
Comparing screw-planning options such as C1–C2 or C3–C6 constructs after checking the required scans and segmentations.
Why use it?
It puts multiple surgical planning scenarios side by side so clinicians can compare viable techniques for a case.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is zhangreling02-ai/3dslicer-claude-bridge's own configuration. It tells Claude Code how to work on 3dslicer-claude-bridge 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 3dslicer-claude-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zhangreling02-ai/3dslicer-claude-bridge. 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/zhangreling02-ai/3dslicer-claude-bridge/main/.claude/commands/construct-compare.md
Clone the repo
git clone --depth 1 https://github.com/zhangreling02-ai/3dslicer-claude-bridge

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 construct-compare

README.md
[![agentmods](https://agentmods.dev/badge/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare/github.svg)](https://agentmods.dev/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare)
Your own site
<a href="https://agentmods.dev/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare"><img src="https://agentmods.dev/badge/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare/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 construct-compare

Your own site · 80×15
<a href="https://agentmods.dev/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare"><img src="https://agentmods.dev/badge/commands/zhangreling02-ai/3dslicer-claude-bridge/construct-compare.svg" alt="Reviewed on agentmods" width="80" 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 750 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 $0.00750
Opus 5 $0.00000 $0.00375
Sonnet 5 $0.00000 $0.00150
Haiku 4.5 $0.00000 $0.00075

Measured 9d ago against content hash 7d6e1b3190b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

construct-compare 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.

.claude/commands/construct-compare.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/construct-compare - Compare Instrumentation Options

Compare alternative screw constructs for the same case.

Description

Runs multiple screw planning scenarios with different techniques and generates a comparative analysis to aid surgical decision-making.

Usage

/construct-compare C1-C2          # Compare all viable C1-C2 techniques
/construct-compare C3-C6          # Compare subaxial options

Instructions

When the user invokes this command:

1. Parse levels from $ARGUMENTS

If no levels specified, ask the user.

2. Verify data

Call list_scene_nodes(). Requires CT + segmentation + CTA (if C1-C2 involved).

If segmentation is missing, run segment_spine(). If C1-C2 involved and no VA segmentation, run segment_vertebral_artery().

3. Get auto recommendation first

plan_cervical_screws(
    volume_node_id=<ct_id>,
    segmentation_node_id=<seg_id>,
    levels=<levels>,
    technique="auto",
    va_segmentation_id=<va_seg_id>
)

Note the recommended technique and viable alternatives from the output.

4. Run each viable technique

For each viable technique returned by the auto analysis, run:

plan_cervical_screws(
    ...,
    technique=<specific_technique>
)

Common alternatives for C1-C2:

  • Harms (C1 lateral mass + C2 pars/pedicle)
  • Magerl (transarticular C1-C2)
  • Wright (C1 lateral mass + C2 translaminar)

Common alternatives for subaxial:

  • Lateral mass (Magerl technique)
  • Lateral mass (An technique)
  • Pedicle screws (if anatomy allows)

5. Generate comparative table

CONSTRUCT COMPARISON - [levels]

OPTION A: [technique name] (RECOMMENDED)
  - Screws: [summary]
  - VA clearance: [mm]
  - Bone quality match: [good/fair/poor]

OPTION B: [technique name]
  - Screws: [summary]
  - VA clearance: [mm]
  - Bone quality match: [good/fair/poor]

OPTION C: [technique name]
  - Screws: [summary]
  - VA clearance: [mm]
  - Bone quality match: [good/fair/poor]

COMPARISON TABLE:
  Criteria         | Option A | Option B | Option C
  Biomechanical    | [rating] | [rating] | [rating]
  VA Risk          | [rating] | [rating] | [rating]
  Technical Ease   | [rating] | [rating] | [rating]
  Bone Req.        | [rating] | [rating] | [rating]
  Viable           | YES/NO   | YES/NO   | YES/NO

RECOMMENDATION:
  [Technique name] because [anatomical justification]

CONTRAINDICATIONS:
  - [Any techniques ruled out and why]

Read the full file on GitHub · 110 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 · 110 lines · 0 tokens per session scan A 7d6e1b3190b1

Subscribe to this mod's changes

construct-compare is a command published in the GitHub repository zhangreling02-ai/3dslicer-claude-bridge (0 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 750 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.