A bridge that imports EPA SWMM or EPANET water-system models from .inp files into a MIKE+ SQLite database. SWMM and EPANET are programs for modelling drainage and water-distribution systems.

It is for converting an .inp model, creating a new MIKE+ database, importing nodes, links, catchments, and simulations, and checking import results.

It handles MIKE+ import requirements, keeps the original input file unchanged, and reports what was imported and activated.

mike-import — Skill for Claude Code and Codex by Zhonghao1995

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 Zhonghao1995/Agentic-MIKE-Plus --skill mike-import

Clone the repo

git clone --depth 1 https://github.com/Zhonghao1995/Agentic-MIKE-Plus

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhonghao1995/agentic-mike-plus/mike-import.svg)](https://agentmods.dev/skills/zhonghao1995/agentic-mike-plus/mike-import)

Your own site

<a href="https://agentmods.dev/skills/zhonghao1995/agentic-mike-plus/mike-import"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-mike-plus/mike-import.svg" alt="Measured on agentmods" 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 810 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.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.00810
Opus 5	$0.00048	$0.00405
Sonnet 5	$0.00019	$0.00162
Haiku 4.5	$0.00010	$0.00081

Measured 8d ago against content hash 09c4b16651f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mike-import 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 8d 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/mike-import/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MIKE+ Import

Creates a new .sqlite from an .inp. SWMM data lands in MIKE+'s SWMM tables (mss_Node, mss_Link, mss_Project, ... ; subcatchments in msm_Catchment) and the tool switches the model type to CS_SWMM so the imported simulation setup is the active one. mike_model_info then reports the mss_* counts and setups.

Tool

mike_import_swmm — {inp, out_sqlite, kind?='swmm'|'epanet', overwrite?, srid?, projection?} → {sqlite, inp_used, patched_outfalls_gated[], active_model, active_simulation, unit_system, simulations[], counts{nodes,links,catchments}, inp_scan}.

What the tool does for you (verified on MIKE+ 2026)

Gated column. MIKE+ rejects [OUTFALLS] rows without the optional Gated column (O1 90 FREE, valid for EPA SWMM which assumes NO) with an opaque "Error importing from SWMM file." The tool writes a patched COPY <name>.mikeplus.inp next to out_sqlite (adds NO), imports that, and lists the rows in patched_outfalls_gated. Your original .inp is never modified.
Model type. Sets m_ModelSetting.ModelNo = 2 (SWMM) so active_model = CS_SWMM and the imported mss_Project setup is active.
Failure hints. On failure the error names the likely cause: gated-less outfalls, or the model is bigger than the demo-mode limit (more than 10 subcatchments fails when no license is checked out).

Conventions

Needs a real license for anything but toy models: if the error mentions the demo limit, the GUI or another process holds the seat: free it, wait, retry once; do not loop.
overwrite defaults to false; the tool refuses to clobber an existing .sqlite.
External files referenced by the .inp (FILE "rain.dat" time series) are not copied; keep them next to the .inp and check inp_scan.TIMESERIES vs what the model expects.
After import: mike_model_info (expect CS_SWMM, mss_* counts) → copy the folder → mike_run. Running an imported SWMM-type model through mike_run has not been verified live yet (license); gate on status as always and report what you see.
EPANET (kind='epanet') uses the same call; the model type is left as MIKE+ sets it (report active_model).

Read the full file on GitHub · 40 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.

8d ago First seen · 40 lines · 97 tokens per session scan A 09c4b16651f3

Subscribe to this mod's changes

mike-import is a skill published in the GitHub repository Zhonghao1995/Agentic-MIKE-Plus (7 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 810 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 2026-08-31.

Hydrology LLM Scientific agentic-ai dhi hydraulic-modeling mcp

autonomous-researcher

End-to-end research pipeline: scoping, literature review, hypothesis formation, synthesis, empirical validation, and written output.

aaronnat23/disp8ch · 0 tokens

research-librarian

Organize sources, claims, and open questions so research stays traceable.

aaronnat23/disp8ch · 0 tokens

Jupyter Live Kernel

Guides notebook-first analysis with reproducible kernels, inspectable data loading, and explicit promotion paths back into durable code.

agentic-in/elephant-agent · 29 tokens

arXiv

Search, filter, and summarize arXiv papers with explicit titles, authors, dates, and paper links before drawing conclusions.

agentic-in/elephant-agent · 29 tokens

ras-end-to-end

Standard operating procedure for an auditable, headless HEC-RAS workflow via the hec-ras MCP server — how to plan, copy, edit boundaries, run, QA-gate, read results, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a HEC-RAS project (.prj folder) or a results file (.p##.hdf) plus a…

Zhonghao1995/Agentic-HEC-RAS · 113 tokens

ras-results

Read, compare and plot HEC-RAS results (.p##.hdf) via the hec-ras MCP server without HEC-RAS — one-screen run summary (QA, volume accounting, cross-section peaks, 2D wet cells / max depth, reference lines), one time series with peak and timing (cross section, reference line / point, boundary, 2D cell)…

Zhonghao1995/Agentic-HEC-RAS · 154 tokens