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.
npx skills add Zhonghao1995/Agentic-HEC-RAS --skill ras-modelgit clone --depth 1 https://github.com/Zhonghao1995/Agentic-HEC-RASWrote 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-hec-ras/ras-model)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-hec-ras/ras-model"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-hec-ras/ras-model.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00142 | $0.00949 |
| Opus 5 | $0.00071 | $0.00475 |
| Sonnet 5 | $0.00028 | $0.00190 |
| Haiku 4.5 | $0.00014 | $0.00095 |
Grade A, and why
ras-model 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 7d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ras-model: inspect + edit (no GUI, no HEC-RAS needed)
Tools
| Tool | Does | Needs |
|---|---|---|
ras_project_info |
project overview: plans (title, short id, g##, u##/f##, sim window, intervals, cores, results HDF present?), geometries, flow files + boundaries, current plan, detected Ras.exe; plan -> that plan's boundaries in detail (boundary_index, river/reach/rs or area/bc_line, kind, interval, n, peak; include_values for the series) |
.prj |
ras_project_copy |
copy the whole project folder to dest (results/logs excluded unless include_results) |
folder |
ras_plan_set |
edit one .p##: simulation_start / simulation_end, computation_interval, output_interval, mapping_interval, num_cores, short_id, title, description, geom, flow |
a copy |
ras_flow_set_hydrograph |
edit ONE boundary table in a .u##: values (replace, any length), multiplier (scale existing values), qmult (HEC-RAS QMult multiplier, values untouched), interval; select by boundary_index or river/reach/rs or area/bc_line |
a copy |
Procedure
ras_project_info(project)-> pick the plan; noteflow_kind(onlyunsteadyplans have an editable.u##).ras_project_copy(project, dest=runs/<case>/00_<name>)for EVERY variant (baseline too).ras_project_info(project=<copy>, plan=..)-> readplan_detail.boundaries; use itsindex.- Edit the copy:
- inflow +20 %:
ras_flow_set_hydrograph(project=<copy>, plan="03", boundary_index=0, multiplier=1.2) - new event:
ras_flow_set_hydrograph(..., values=[...], interval="15MIN")(values in the project's units) - shorter time step / window / cores:
ras_plan_set(project=<copy>, plan="03", computation_interval="5SEC", num_cores=4)
- inflow +20 %:
- Re-run
ras_project_info(plan=..)and quote thebefore/afterfrom the tool return in the report.
Rules
- Never edit the original folder; every edit tool rewrites files in place.
- One boundary per
ras_flow_set_hydrographcall; the tool refuses ambiguous selectors — add river/reach/rs. multiplierandvaluesare mutually exclusive;qmultleaves the table alone (HEC-RAS scales at run time) — prefermultiplierwhen the edited file must show the actual numbers.- Precipitation: only a
Precipitation HydrographTABLE in the.u##is editable; gridded (DSS) precipitation is not. - Steady-flow files (
.f##), geometry (.g##), terrain, land cover, 2D mesh, structures: not editable here (GUI / RAS Mapper). - Intervals must be HEC-RAS strings (
1SEC ... 1DAY); dates02JAN1900 0000or ISO1900-01-02T00:00. - Units follow the project (US customary: cfs / ft; SI: m3/s / m) — check
ras_results_summary.units_systemon any HDF or the plan HDF root.
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.
- 7d ago First seen · 39 lines · 142 tokens per session scan A c2d14059d9bb
ras-model is a skill published in the GitHub repository Zhonghao1995/Agentic-HEC-RAS (1 stars, last pushed 21d ago), licensed MIT. It adds 142 tokens to every session and 949 once invoked, about $0.0007 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.
Other skills, from other repositories
mike-end-to-end
Standard operating procedure for an auditable, headless MIKE+ workflow via the mike-plus MCP server — how to plan, copy, run, QA-gate, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a MIKE+ model (.sqlite) or result (.res1d) plus a plain-language goal; it picks the operating mode and…
mike-plot
Produce publication-style figures from MIKE+ .res1d results via the mike-plus MCP server — a stacked rainfall-runoff hydrograph, a single time series, a network map, a baseline-vs-scenario overlay, or a longitudinal profile (bed / crown / ground / max water level along a pipe string), in the house style (Arial 12…
mike-compare
Compare two MIKE+ runs via the mike-plus MCP server — baseline vs scenario, before vs after a parameter edit — to say WHERE a change mattered and BY HOW MUCH (delta peak, delta volume, timing shift, RMSE/NSE) and to draw the overlay hydrograph. Use whenever two .res1d files of the same model exist or a re-run just…
mike-import
Bring an EPA SWMM (.inp) or EPANET (.inp) model into MIKE+ via the mike-plus MCP server — the bridge from an INP builder such as SWMMCanada or agentic-swmm into a MIKE+ database that mikemodelinfo / mikerun can use. Use when the user has an .inp and wants it in MIKE+. Requires MIKE+ installed + a checked-out license…
mike-rain
Turn a timestamped rainfall CSV (design storm, gauge record, climate-scenario series) into a MIKE+ rainfall .dfs0 via the mike-plus MCP server, verified by read-back, ready to drive a model's rainfall boundary or to sit on top of a hydrograph figure. Use when the user brings rain as CSV or asks to run a model with a…
mike-results
Read MIKE+ .res1d results via the mike-plus MCP server — list contents, summarize peaks, extract a single time series, or check which nodes flood (peak water level vs ground level). Use when an agent needs to inspect or pull numbers from MIKE+ network results (node water levels, link/reach discharge, velocities…