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-MIKE-Plus --skill mike-resultsgit clone --depth 1 https://github.com/Zhonghao1995/Agentic-MIKE-PlusWrote 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-mike-plus/mike-results)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-mike-plus/mike-results"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-mike-plus/mike-results/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-mike-plus/mike-results"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-mike-plus/mike-results.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.00851 |
| Opus 5 | $0.00042 | $0.00426 |
| Sonnet 5 | $0.00017 | $0.00170 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
mike-results 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 10d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MIKE+ Results
Reads MIKE+ .res1d result files (via mikeio1d). No license / no MIKE+ install needed — fully portable.
When to use
To find out what is in a result file, get peak values, extract a series for analysis/plotting, or answer "which manholes flood?". Use after mike_run, or on any existing .res1d. (Two result files side by side: mike-compare.)
Tools
mike_results_list—{res1d}→ quantities, element counts + sample ids (nodes/reaches/structures/catchments), time range. Start here to discover validquantity/elementvalues.mike_results_summary—{res1d, quantities?, skip_hours?}→ per-quantity peak (value, element, chainage, time), in the canonical schema.mike_results_read—{res1d, quantity, element, max_points?}→ a single downsampled time series (times,values,unit,peak_value,peak_time).mike_results_flooding—{res1d, skip_hours?, top_n?, include_outlets?}→ per node: peak water level vsground_level(andcritical_level) →n_flooded,flooded[]ranked by exceedance (freeboard_m< 0, withpeak_time, nodetype),n_above_critical,closest_to_flooding[]. Outlets are skipped by default (their level is the boundary, not flooding).
Conventions
- Column identity is
Quantity:ElementId[:chainage](e.g.Discharge:Link_29:33.5333).elementmatches the id prefix. - Output follows the canonical, engine-agnostic schema (
{engine, quantity, element_id, chainage, unit, ...}) so the same downstream skills work for SWMM/LSTM later. (mike_results_summaryreports the peak's element aspeak_element— same idea, named for the peak.) - Global-max caveat:
mike_results_summaryreturns the max over the WHOLE run, which can land in the warm-up / initial-condition period (e.g. a base-flow value near t=0), not the storm peak. Always checkpeak_time; when you want the event peak, passskip_hours(e.g.skip_hours: 6) to drop the initial window. The same applies tomike_results_flooding. - Flooding is judged against the ground level stored in the result file. Nodes with an obviously artificial
critical_level(e.g. 100 m) or river/basin nodes may carry a nominal ground level: report thetypeand level, and let the user judge; do not filter them silently (only outlets are excluded by default, and that is stated in the output). - Report only what the file contains; if a
quantity/elementhas no series, say so (the tool errors with a clear message) rather than guessing.
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.
- 10d ago First seen · 34 lines · 84 tokens per session scan A f600aaf9a0ff
mike-results is a skill published in the GitHub repository Zhonghao1995/Agentic-MIKE-Plus (7 stars, last pushed 25d ago), licensed MIT. It adds 84 tokens to every session and 851 once invoked, about $0.0004 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
autonomous-researcher
End-to-end research pipeline: scoping, literature review, hypothesis formation, synthesis, empirical validation, and written output.
research-librarian
Organize sources, claims, and open questions so research stays traceable.
Jupyter Live Kernel
Guides notebook-first analysis with reproducible kernels, inspectable data loading, and explicit promotion paths back into durable code.
arXiv
Search, filter, and summarize arXiv papers with explicit titles, authors, dates, and paper links before drawing conclusions.
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…
ras-model
Inspect and edit a HEC-RAS project without the GUI via the hec-ras MCP server — list plans / geometries / flow files / boundary conditions (rasprojectinfo), copy the whole project safely (rasprojectcopy), change plan settings such as simulation window, time step, output interval, cores, geometry or flow file…