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-auditgit 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-audit)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-hec-ras/ras-audit"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-hec-ras/ras-audit/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-hec-ras/ras-audit"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-hec-ras/ras-audit.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 | $0.00099 | $0.00504 |
| Opus 5 | $0.00049 | $0.00252 |
| Sonnet 5 | $0.00020 | $0.00101 |
| Haiku 4.5 | $0.00010 | $0.00050 |
Grade A, and why
ras-audit 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.
What it actually says
ras-audit: provenance manifest
Tool
ras_manifest_write(out_json, case?, project?, plan?, inputs?, results?, figures?, run?, edits?, tool_calls?, notes?)
- writes
out_json(schemaagentic-hecras/manifest/1): every listed file with{path, exists, bytes, sha256}, the QA subset of theras_runreturn (status,usable,reasons,metrics,hdf,ras_version,elapsed_s), the edit records (ras_plan_set/ras_flow_set_hydrographreturns), the ordered tool calls, free notes, and the Python / platform / package versions - returns
missing_files— must be[]before claiming reproducibility
Procedure
- Collect: the copied
.prj(project),plan, the edited.u##/.p##(inputs), the.p##.hdffiles (results), the PNGs (figures), the fullras_runreturn (run), the edit returns (edits), and the list of{tool, args, ok}calls made so far (tool_calls). ras_manifest_write(out_json=runs/<case>/manifest.json, ...)as the LAST call of the case.- Report the manifest path and
missing_files(must be empty).
Rules
- One manifest per case (baseline + variant together is fine: list both HDFs in
results, the variant's run inrun). - Never write the manifest before the runs finished; the sha256 of a half-written HDF is useless.
- Keep
notesto the plain-language goal + anything not derivable from files (why the edit, what was skipped).
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 · 32 lines · 99 tokens per session scan A 696882b4a33d
ras-audit is a skill published in the GitHub repository Zhonghao1995/Agentic-HEC-RAS (1 stars, last pushed 23d ago), licensed MIT. It adds 99 tokens to every session and 504 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.
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-params
Read and modify MIKE+ model parameters via the mike-plus MCP server — inspect or change values in any model table (pipe Diameter/Manning in msmLink, node levels in msmNode, catchment properties in msmCatchment, etc.). Use when an agent must identify a current parameter and change it before re-running. Requires MIKE+ +…
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…