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-swmm-workflow --skill swmm-reportgit clone --depth 1 https://github.com/Zhonghao1995/agentic-swmm-workflowWrote 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-report)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-swmm-workflow/swmm-report"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-swmm-workflow/swmm-report/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-report"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-swmm-workflow/swmm-report.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 | $0.00062 | $0.01671 |
| Opus 5 | $0.00031 | $0.00835 |
| Sonnet 5 | $0.00012 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
swmm-report 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 6d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWMM Report Export Skill
Purpose
Assemble a reproducible, client-deliverable Word (.docx) report from the
artifacts produced by swmm-experiment-audit and swmm-plot. The script
reads only existing files; it never re-runs SWMM or modifies the run
directory.
Prerequisite: the run directory must contain a 09_audit/ subdirectory
with at least experiment_provenance.json. Run aiswmm audit --run-dir <path> first if that directory is absent.
CLI usage
# Standalone script
python3 skills/swmm-report/scripts/generate_report.py \
--run-dir <path> # required: audited run directory
[--out <path.docx>] # default: <run-dir>/report.docx
[--template <path>] # YAML or JSON template (default: built-in)
# CLI verb (registered in aiswmm CLI)
aiswmm report --run-dir <path> [--out <path.docx>] [--template <template.yaml>]
Exit codes: 0 = success; 1 = missing dependency, missing audit dir, or
template error; 2 = argument error.
python-docx dependency: install with pip install 'aiswmm[report]'.
The script exits immediately with a clear message if python-docx is absent.
Agent tool: generate_report
Registered in AgentToolRegistry. Direct handler (not MCP-routed) —
shells out to generate_report.py, writes <run-dir>/report.docx (or
the path supplied via out).
generate_report(run_dir="runs/my_run/")
generate_report(run_dir="runs/my_run/", out="deliverables/run_report.docx")
generate_report(run_dir="runs/my_run/", template="templates/client_a.yaml")
is_read_only=False — QUICK profile prompts the user (tool writes files).
If python-docx is not installed the tool returns a failure dict whose
summary carries the install hint pip install 'aiswmm[report]'.
Executed example
# Create a minimal synthetic fixture
mkdir -p /tmp/swmm_report_fixture/09_audit
cat > /tmp/swmm_report_fixture/09_audit/experiment_provenance.json << 'EOF'
{
"schema_version": "1.0",
"run_id": "smoke-test-run",
"generated_at_utc": "2025-01-01T00:00:00Z",
"metrics": {"peak_flow": {"value": 1.23, "time_hhmm": "06:30"},
"continuity_error": -0.5, "swmm_return_code": 0},
"qa": {"checks": [{"id": "continuity", "ok": true, "detail": "within tolerance"}]},
"repo": {"git_head": "abc1234", "git_branch": "main"},
"tools": {"swmm5_version": "5.1.015", "python_version": "3.11"},
"artifacts": {
"model.inp": {"role": "input", "sha256": "4840dbe4abcdef", "exists": true,
"produced_by": "builder"}
},
"generated_by": "aiswmm"
}
EOF
python3 skills/swmm-report/scripts/generate_report.py \
--run-dir /tmp/swmm_report_fixture \
--out /tmp/swmm_report_smoke.docx
# Output: Report written to: /tmp/swmm_report_smoke.docx
What ships with it
2 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.
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.
- 6d ago Changed · +2 lines f3d017a83781
- 10d ago First seen · 167 lines · 62 tokens per session scan A 36361a8a46cf
swmm-report is a skill published in the GitHub repository Zhonghao1995/agentic-swmm-workflow (27 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 1,671 once invoked, about $0.0003 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
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
add-pdf-reader
Add PDF reading to ClaudeClaw agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.
financial-expense-automation
An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.
wes-clinical-report-en
Generates professional clinical PDF reports in English from WES (Whole Exome Sequencing) data with clinical interpretation summary, pharmacogenomic alerts, and follow-up recommendations.
wes-clinical-report-es
Generates professional clinical PDF reports in Spanish from WES (Whole Exome Sequencing) data with clinical interpretation, pharmacogenomic alerts, and follow-up recommendations.
qgis-impl-print-layouts
Use when creating print layouts, exporting maps to PDF/SVG/image, or generating atlas series. Prevents empty map exports from missing extent configuration and atlas misconfiguration. Covers QgsPrintLayout, layout items (map, label, legend, scale bar), atlas generation, and PDF/SVG/image export. Keywords: print layout…