Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Zhonghao1995/agentic-swmm-workflownpx agentmods add skills/zhonghao1995/agentic-swmm-workflow/swmm-gisWrote 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.
[](https://agentmods.dev/skills/zhonghao1995/agentic-swmm-workflow/swmm-gis)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-swmm-workflow/swmm-gis"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-swmm-workflow/swmm-gis/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.
<a href="https://agentmods.dev/skills/zhonghao1995/agentic-swmm-workflow/swmm-gis"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-swmm-workflow/swmm-gis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.04950 |
| Opus 5 | $0.00065 | $0.02475 |
| Sonnet 5 | $0.00026 | $0.00990 |
| Haiku 4.5 | $0.00013 | $0.00495 |
Grade A, and why
swmm-gis 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.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWMM GIS / Preprocess
Part of Agentic SWMM — install the project first for the executable toolchain (aiswmm CLI, SWMM solver, MCP servers).
Before calling any watershed delineation tool — ask the user
When the user triggers watershed delineation (qgis_raw_to_entropy_partition or equivalent), always ask these questions first before making the tool call:
- Delineation mode — Standard (fast, direct GRASS basins, no entropy) or Entropy-guided (paper WJE/NWJE/WFJS split-lump with sensitivity figures)?
- Stream threshold — How many upslope cells define a stream? Default 100. Smaller = more streams = finer subcatchments.
- If entropy mode — Delta threshold (default 0.015) and WFJS similarity threshold (default 0.95)? Use defaults unless doing sensitivity exploration.
- Purpose — Planning / calibration exploration / sensitivity analysis / paper reproduction? This affects how strictly to apply paper-only splits and whether sensitivity figures are needed.
- CRS normalization needed? — Are all input layers already in the same projected CRS? If uncertain, check first with
qgis_load_layers+qgis_validate_crs.
Do not assume entropy mode. Do not skip the stream threshold question — it directly controls subcatchment count.
Default CRS policy: if source layers already share the same projected CRS, do not run normalize-layers. The normalization bridge reprojects, clips, and may resample raster grids, so it can change watershed structure. Only use it when layer CRS/raster alignment actually needs preprocessing. If CRS differs but geometry should be preserved, prefer a reproject-only step over clipping/resampling.
Choosing the right delineation mode
| Standard | Entropy-guided | |
|---|---|---|
| Speed | Fast (~minutes) | Slow (~10–30 min, 5 sensitivity variants) |
| Output | GRASS basin polygons only | WJE/NWJE/WFJS partition + sensitivity figures + entropy hotspot ranking |
| Use when | Quick first look, simple watersheds, testing pipeline connectivity | Research, paper reproduction, heterogeneous land-use/soil, need to justify subcatchment count |
| MCP flag | mode: "standard" |
mode: "entropy" (default) |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/qgis_overlay_subcatchments.geojson 1.2 KB
- examples/subcatchments_dem_assisted.geojson 832 B
- examples/subcatchments_dem_stats_demo.json 412 B
- examples/subcatchments_demo.geojson 1.1 KB
- scripts/area_weighted_swmm_params.py 23 KB runs code
- scripts/basin_shp_to_subcatchments.py 7.5 KB runs code
- scripts/find_pour_point.py 4.5 KB runs code
- scripts/plot_qgis_standard_layers.py 4.6 KB runs code
- scripts/preprocess_subcatchments.py 30 KB runs code
- scripts/qgis_package_final_layers.py 7.6 KB runs code
- scripts/qgis_prepare_swmm_inputs.py 33 KB runs code
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.
- 12d ago First seen · 296 lines · 130 tokens per session scan A 4a114bfbdd49
swmm-gis is a skill published in the GitHub repository Zhonghao1995/agentic-swmm-workflow (27 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 4,950 once invoked, about $0.0006 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.
Other skills, from other repositories
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
academic-literature-search
A multi-database search tool for academic papers and other scholarly publications. It searches sources such as Semantic Scholar, Crossref, arXiv, and PubMed, which cover research across fields including computing, physics, and medicine.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
earth2studio-data-fetch
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.