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 hongzhizuo/johgee-open-irrigation --skill ai-toolsgit clone --depth 1 https://github.com/hongzhizuo/johgee-open-irrigationWrote 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/hongzhizuo/johgee-open-irrigation/ai-tools)<a href="https://agentmods.dev/skills/hongzhizuo/johgee-open-irrigation/ai-tools"><img src="https://agentmods.dev/badge/skills/hongzhizuo/johgee-open-irrigation/ai-tools/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/hongzhizuo/johgee-open-irrigation/ai-tools"><img src="https://agentmods.dev/badge/skills/hongzhizuo/johgee-open-irrigation/ai-tools.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 | $0.00100 | $0.00640 |
| Opus 5 | $0.00050 | $0.00320 |
| Sonnet 5 | $0.00020 | $0.00128 |
| Haiku 4.5 | $0.00010 | $0.00064 |
Grade A, and why
johgee-calculate-watering 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 11d 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
Johgee calculate watering
v2 can use on-demand Met Office free weather when a UK postcode is given.
If weather cannot be fetched, the plan falls back to the gardener's
self-report and is labelled manual. Restriction status stays unknown.
Call calculate_watering without a postcode, or get_watering_advice with
one. Do not invent millimetres, litres, runtime, restriction status or
variant ids.
When to call
- The garden is in the United Kingdom.
- The user can describe garden type, area or container count, soil, sun, establishment, watering method, recent rain, and soil feel.
- They want a plan, not a product pitch.
When not to call
- They ask whether a hosepipe ban is in force. Tell them to check their water company: https://www.water.org.uk/customers/find-your-supplier
- They want the tool to turn taps or timers on.
- The garden is outside the UK.
Input meaning
recent_rainfall:none/light/heavyover the last 48–72 hours.soil_feel: finger test —dry/moist/wet.forecast_rainfall: optional expected rain. If unsure, omit it.irrigation_method:watering_canis a watering can;hoseis a hosepipe.calculate_wateringdoes not need a postcode.get_watering_advicerequires a UK postcode; it is not stored.
Output rules
- Repeat numbers exactly as returned, with units (mm, litres, minutes).
- State that data mode is
manualand that this is a decision aid, not a guarantee. - If the tool returns a problem (422), ask for the missing field. Do not guess.
- If status is
UNAVAILABLEfor hosepipe or sprinkler, do not soften it.
Local MCP
{
"mcpServers": {
"johgee": {
"command": "pnpm",
"args": ["--filter", "@johgee/ai-tools", "start"]
}
}
}
Run pnpm --filter @johgee/contracts build && pnpm --filter @johgee/irrigation-core build && pnpm --filter @johgee/ai-tools build first. The server uses stdio and needs no network.
What ships with it
13 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.
- mcp.cursor.example.json 123 B
- package.json 727 B
- README.md 641 B
- src/calculate-watering.test.ts 3.6 KB runs code
- src/calculate-watering.ts 5.3 KB runs code
- src/get-watering-advice.test.ts 4.1 KB runs code
- src/get-watering-advice.ts 6.0 KB runs code
- src/http.ts 276 B runs code
- src/index.ts 424 B runs code
- src/server.ts 2.7 KB runs code
- src/stdio.ts 247 B runs code
- tsconfig.build.json 238 B
- tsconfig.json 162 B
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.
- 11d ago First seen · 66 lines · 100 tokens per session scan A 1fa846cf63f4
johgee-calculate-watering is a skill published in the GitHub repository hongzhizuo/johgee-open-irrigation (0 stars, last pushed 18d ago), licensed MIT. It adds 100 tokens to every session and 640 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
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
bio-differential-expression-batch-correction
Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
alphafold2
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency…
figure-rhetoric
Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs…