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-runnergit 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-runner)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-mike-plus/mike-runner"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-mike-plus/mike-runner.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 | $0.00085 | $0.00602 |
| Opus 5 | $0.00043 | $0.00301 |
| Sonnet 5 | $0.00017 | $0.00120 |
| Haiku 4.5 | $0.00009 | $0.00060 |
Grade A, and why
mike-runner 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.
What it actually says
MIKE+ Runner
Executes a MIKE+ model headless through the mike-plus MCP server (engine: MIKE 1D).
When to use
After a model is ready and you need to actually run it — the active simulation, or a named setup from msm_Project. Do not use this to read results (that's mike-results) or to plot (mike-plot). The whole-workflow rules (run directory, copy policy, stop rules, QA gates) are in mike-end-to-end; a baseline-vs-variant pair of runs is compared with mike-compare.
Tool
mike_run— args:sqlite(path),simulation(optional setup id),timeout_s(optional). Returns{ok, active_simulation, result_files[], elapsed_s}, a parsed QA gate{completed, errors, warnings, issues, status, log_file}, and_log_tail(engine console).
Conventions (evidence boundaries)
- License + install required.
mike_runloads the local MIKE 1D engine; it fails on a machine without MIKE+ + a valid license. (Reading/plotting do not.) - Always run on a COPY. mikeplus has no undo — copy the model folder first and run the copy, never the user's original.
- Gate on the QA fields, not just
ok.okonly means the call returned. Checkstatus:ok/completed_with_warningsare usable;completed_with_errorsorincompletemean the run is untrustworthy — surfaceerrors/warningsand point atlog_filefor detail, don't bury them.status="unknown"means no engine log was found. - Do not fabricate metrics. Pass the returned
result_filestomike-results/mike-plot, and the whole return value tomike_manifest_write(mike-audit).
Orchestration
mike_model_info -> confirm the active simulation / pick one (mike_set_scenario if a GUI scenario is wanted)
mike_run -> result_files (.res1d) + status
-> mike-results (summary / flooding / read) -> mike-plot -> mike-audit
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 · 29 lines · 85 tokens per session scan A 2c845fa1920b
mike-runner is a skill published in the GitHub repository Zhonghao1995/Agentic-MIKE-Plus (7 stars, last pushed 22d ago), licensed MIT. It adds 85 tokens to every session and 602 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…