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 skill-authorgit 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/skill-author)<a href="https://agentmods.dev/skills/zhonghao1995/agentic-swmm-workflow/skill-author"><img src="https://agentmods.dev/badge/skills/zhonghao1995/agentic-swmm-workflow/skill-author.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.01027 |
| Opus 5 | $0.00051 | $0.00513 |
| Sonnet 5 | $0.00020 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
skill-author 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill author
Turn a description of a recurring need into a draft skill that a human can review and approve. This skill writes proposals; it never installs, activates, or edits skills on its own — a freshly drafted skill is a proposal, not a verified capability.
It is domain-general: nothing here is specific to stormwater or SWMM. The same recipe produces a skill for any modeling or workflow domain.
When to use
- A recurring problem keeps showing up and no existing skill covers it — the gap itself is the trigger to propose a new one.
- Someone asks to "create / propose / draft a new skill" for some capability.
- An agentic system (e.g. a memory or lessons-learned layer) flags a repeated pattern that warrants a new skill rather than a tweak to an existing one.
If an existing skill already covers most of the need, improve that one instead — don't create a near-duplicate (see step 2).
How to draft a skill
-
Capture intent. Pin down three things before writing: (a) what should this skill let the agent do? (b) when should it trigger — what phrases or contexts? (c) what does it produce (output format)? Pull answers from the conversation or the evidence you were handed; only ask the human for what's genuinely missing.
-
Check for overlap first. List the existing skills and check whether one already does most of this. If so, propose refining that skill instead of adding a new one — avoiding skill sprawl keeps the library discoverable.
-
Fill the template. Copy
assets/SKILL.template.mdand fill it in. The two fields that matter most:name— kebab-case, matches the folder name.description— this is how the agent decides to use the skill, so make it specific and slightly pushy: say what it does AND the concrete situations it should trigger in. A vague description means the skill never fires.
Keep the body lean and explain the why behind each instruction — a capable model follows reasoning better than rigid ALL-CAPS rules. See
references/skill-format.mdfor the full recipe (anatomy, progressive disclosure, writing patterns).
What ships with it
4 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.
- 8d ago First seen · 62 lines · 102 tokens per session scan A d1ea29f00789
skill-author is a skill published in the GitHub repository Zhonghao1995/agentic-swmm-workflow (25 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,027 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 2026-08-30.
Other skills, from other repositories
agenticmail
🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.
ai-meeting-scheduling
Booking links fail for groups. SkipUp schedules meetings with 2-50 participants via email — one API call coordinates across timezones automatically. Also: check status, pause, resume, or cancel requests. Async only — does not instant-book, access calendars, or do free/busy lookups.
agentic-paper-digest-skill
Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest. Use when the user wants a paper digest, a JSON feed of recent papers, or to run the arXiv/HF pipeline.
eachlabs-voice-audio
Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
academic-literature-search
A multi-database search tool for academic papers and other scholarly publications. It searches sources such as Semantic Scholar, Crossref, arXiv, and PubMed, which cover research across fields including computing, physics, and medicine.