ras-commander: Skill for Claude Code

.claude/skills/qa_repair_geometry/SKILL.md

qa_repair_geometry is a skill for Claude Code from gpt-cmdr/ras-commander. It costs 97 tokens per session (3,496 once invoked), scanned A, original, MIT.

A workflow for repairing errors in HEC-RAS model geometry and checking the repaired model. Geometry describes the shapes and structures that control how water moves through the model.

In plain words
What is it for?
It is for fixing obstructions, checking model quality, creating comparison visualisations and audit trails, and supporting FEMA compliance checks.
Why use it?
It helps address blocked obstructions and other geometry problems while recording before-and-after visual evidence and validation results.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is gpt-cmdr/ras-commander's own configuration. It tells Claude Code how to work on ras-commander 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 ras-commander configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gpt-cmdr/ras-commander. 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/gpt-cmdr/ras-commander/main/.claude/skills/qa_repair_geometry/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

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 qa_repair_geometry

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/qa_repair_geometry/github.svg)](https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_repair_geometry)
Your own site
<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_repair_geometry"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/qa_repair_geometry/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 qa_repair_geometry

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/qa_repair_geometry"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/qa_repair_geometry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,496 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.03496
Opus 5 $0.00048 $0.01748
Sonnet 5 $0.00019 $0.00699
Haiku 4.5 $0.00010 $0.00350

Measured 5d ago against content hash fd3183368c4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qa_repair_geometry 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 5d 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/skills/qa_repair_geometry/SKILL.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repairing Geometry Issues

Lightweight skill for navigating ras-commander's geometry checking and repair capabilities.

When the user asks to fix geometry errors, repair obstructions, validate a model, or ensure FEMA compliance, use this skill. Navigate to primary sources for RasCheck (validation) and RasFixit (repair). Do not duplicate content from primary sources -- this file serves as an index only.

Primary Sources (Read These First)

Quality Validation (RasCheck)

ras_commander/check/AGENTS.md - canonical RasCheck package contract

  • Validation scope and package responsibilities
  • Flow-type auto-detection rule
  • Severity, threshold, and reporting expectations
  • Relationship between check/ validation and fixit/ repair

Automated Repair (RasFixit)

ras_commander/fixit/AGENTS.md - canonical RasFixit package contract

  • Blocked obstruction repair algorithm
  • 0.02-unit gap insertion requirement
  • Elevation envelope details
  • Module organization and patterns

Complete Workflows

examples/200_fixit_blocked_obstructions.ipynb

  • RasFixit demonstration with visualizations
  • Before/after comparison workflow
  • Engineering review requirements

examples/300_quality_assurance_rascheck.ipynb

  • RasCheck validation workflow
  • Multi-check execution and reporting
  • Custom threshold configuration

Quick Start Patterns

Check → Fix → Verify Workflow

from ras_commander import RasCheck, RasFixit

# 1. CHECK: Detect issues
results = RasCheck.run_all("01")
print(f"Errors: {results.get_error_count()}")
print(f"Warnings: {results.get_warning_count()}")

# 2. FIX: Repair blocked obstructions (if detected)
fix_results = RasFixit.fix_blocked_obstructions(
    "model.g01",
    backup=True,      # ALWAYS create timestamped backup
    visualize=True    # ALWAYS generate verification PNGs
)
print(f"Fixed {fix_results.total_xs_fixed} cross sections")

# 3. VERIFY: Confirm repairs
verify_results = RasCheck.run_all("01")

Detection Only (Non-Destructive)

Read the full file on GitHub · 428 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. 5d ago First seen · 428 lines · 97 tokens per session scan A fd3183368c4b

Subscribe to this mod's changes

qa_repair_geometry is a skill published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 3,496 once invoked, about $0.0005 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 2026-09-03.