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 5.5 | $0.00040 | $0.00256 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 100 tokens to every session and 640 once invoked, about $0.0004 per session on Opus 5.5. 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.
johgee-calculate-watering compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| johgee-calculate-wateringhongzhizuo/johgee-open-irrigation | Skill | 0 | 2mo ago | MIT | A | 100 | Claude Code, Codex |
| bio-differential-expression-batch-correctionPKU-YuanGroup/OpenAI4S | Skill | 662 | yesterday | MIT | A | 187 | Claude Code, Codex |
| bio-ortholog-inferencePKU-YuanGroup/OpenAI4S | Skill | 662 | yesterday | MIT | A | 141 | Claude Code, Codex |
| admet_geneticPKU-YuanGroup/OpenAI4S | Skill | 662 | yesterday | MIT | A | 63 | Claude Code, Codex |
| bioprobenchPKU-YuanGroup/OpenAI4S | Skill | 662 | yesterday | MIT | A | 46 | Claude Code, Codex |
| alphafold2PKU-YuanGroup/OpenAI4S | Skill | 662 | yesterday | MIT | A | 117 | Claude Code, Codex |
| figure-rhetoricMathews-Tom/armory | Skill | 341 | yesterday | MIT | A | 123 | Claude Code |