ras-commander: Agent for Claude Code

.claude/agents/hecras-results-analyst.md

hecras-results-analyst is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 152 tokens per session (3,514 once invoked), scanned A, original, MIT.

A reviewer for HEC-RAS simulation results, including whether a run completed and what its hydraulic measurements show. HEC-RAS is software for modelling rivers, floods, and waterways.

In plain words
What is it for?
Use it to inspect compute messages, runtime data, water-surface elevations, velocities, peak timing, mesh limits, and other indicators of simulation quality.
Why use it?
It helps catch failed or unreliable simulations that may look successful at first, such as empty data, unrealistic values, missing results, or numerical instability.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; 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/agents/hecras-results-analyst.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 hecras-results-analyst

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/hecras-results-analyst"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/hecras-results-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,514 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 $0.00152 $0.03514
Opus 5 $0.00076 $0.01757
Sonnet 5 $0.00030 $0.00703
Haiku 4.5 $0.00015 $0.00351

Measured 12d ago against content hash 8664407f2a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hecras-results-analyst 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.

.claude/agents/hecras-results-analyst.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: API-First Mandate

This agent MUST use ras-commander HDF API classes for all results extraction and analysis.

Required Approach

  1. MUST use HdfResultsPlan.get_compute_messages() for execution verification
  2. MUST use HdfResultsPlan.get_runtime_data() for performance metrics
  3. MUST use HdfResultsMesh.get_mesh_max_ws(), get_mesh_max_face_v(), etc. for envelope data
  4. MUST use HdfResultsMesh.get_mesh_max_iter() for numerical performance indicators
  5. MUST NOT use raw h5py.File() to extract results
  6. MUST NOT parse .computeMsgs.txt files directly

Why This Matters

The API provides:

  • Structured compute message parsing with severity classification
  • Pre-extracted runtime metrics in DataFrame format
  • Consistent envelope data extraction across plan types
  • Proper handling of steady vs unsteady differences

Correct Patterns

from ras_commander import init_ras_project, ras
from ras_commander.hdf import HdfResultsPlan, HdfResultsMesh

init_ras_project("/path/to/project", "7.0")

# Execution verification
messages = HdfResultsPlan.get_compute_messages("01", ras_object=ras)
runtime = HdfResultsPlan.get_runtime_data("01", ras_object=ras)

# Check completion
is_complete = runtime is not None
if is_complete:
    duration = runtime['Complete Process (hr)'].values[0]

# Results metrics
max_wse = HdfResultsMesh.get_mesh_max_ws("01", ras_object=ras)
max_vel = HdfResultsMesh.get_mesh_max_face_v("01", ras_object=ras)
max_iter = HdfResultsMesh.get_mesh_max_iter("01", ras_object=ras)

Prohibited Patterns

# WRONG - Do NOT parse compute messages directly
with open("project.p01.computeMsgs.txt") as f:
    for line in f:
        if "Error" in line:
            # ...

# WRONG - Do NOT use raw h5py for results
import h5py
with h5py.File("plan.p01.hdf") as f:
    max_wse = f['/Results/...'][:]

API Gap Handling

If you need metrics not available via API:

  1. Complete the user's task using available API methods
  2. Document the gap in your output
  3. Suggest engaging api-consistency-auditor to add the missing extraction method

Read the full file on GitHub · 370 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 · 370 lines · 152 tokens per session scan A 8664407f2a6e

Subscribe to this mod's changes

hecras-results-analyst is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 3,514 once invoked, about $0.0008 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

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

epidemiology-research-agent

Research agent for epidemiology and public health.

benbrastmckie/nvim · 8 tokens