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 charles-gentry/rb209-mcp --skill rb209-nutrient-planninggit clone --depth 1 https://github.com/charles-gentry/rb209-mcpWrote 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/charles-gentry/rb209-mcp/rb209-nutrient-planning)<a href="https://agentmods.dev/skills/charles-gentry/rb209-mcp/rb209-nutrient-planning"><img src="https://agentmods.dev/badge/skills/charles-gentry/rb209-mcp/rb209-nutrient-planning/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/charles-gentry/rb209-mcp/rb209-nutrient-planning"><img src="https://agentmods.dev/badge/skills/charles-gentry/rb209-mcp/rb209-nutrient-planning.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 | $0.00091 | $0.06422 |
| Opus 5 | $0.00046 | $0.03211 |
| Sonnet 5 | $0.00018 | $0.01284 |
| Haiku 4.5 | $0.00009 | $0.00642 |
Grade A, and why
rb209-nutrient-planning 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.
How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RB209 Nutrient Planning
Produce a fertiliser recommendation for a UK field with the rb209_* MCP tools.
The one calculation tool is rb209_recommendation_recommendations (a POST
taking { body: <DataInput> }). Everything else is lookups that give you the
integer IDs the DataInput needs.
Golden rules — read first
- Interview the user before calling anything. Do not invent field details. A recommendation depends on real facts about a real field (crop, soil, location, previous crop, manures, soil-test results). If you don't have one of these, ask the user a short, specific question — never guess a crop, a yield, or a soil type. See Phase 1.
- Resolve every ID from a lookup tool. IDs like
cropTypeId,soilTypeId,swardTypeIdare API-specific integers. Look them up; never hard-code them from memory. Show the user the options when a choice is theirs to make. - Copy the shape of a known-good request. This repo has two real, accepted
DataInput/response pairs — mirror the one matching your field type and only swap in the values you gathered:- Arable:
test/fixtures/RecommendationsSampleInput.json(+…Sample.json) — winter barley, England & Wales. - Grass:
test/fixtures/RecommendationsGrassInput.json(+…GrassSample.json) — first-cut silage plus grazing, England & Wales.
- Arable:
- If the API returns a validation error, read it — the field is named. The error tells you exactly what to fix. See Troubleshooting for the common ones and their fixes.
- Be efficient — a whole recommendation is usually ~6–10 tool calls, not 30.
Avoid these common wasted calls:
- One recommendation call returns all nutrients. Set every nutrient you
want to
truein the singlenutrientsobject and callrb209_recommendation_recommendationsonce. Do not call it per nutrient or re-call it to "check" — N, P₂O₅, K₂O, MgO, SO₃ and lime all come back together. - Don't look
fieldTypeup — it's fixed:1= Arable & Horticulture,2= Grassland,3= Both. - No soil analysis? Send
"soilAnalyses": []and skip all soil methodology/index lookups. The engine applies RB209 default indices; you do not needrb209_soil_methodologies…,rb209_soil_nutrient_index…, or any index tool. (Those T04 "not found" errors mean you're fetching indexes you don't need.) - Don't use
rb209_recommendation_calculate_nutrient_offtakeor nutrient target-index tools for a standard field recommendation — the main recommendation call already does that maths.
- One recommendation call returns all nutrients. Set every nutrient you
want to
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 · 412 lines · 91 tokens per session scan A 0374d97c2220
rb209-nutrient-planning is a skill published in the GitHub repository charles-gentry/rb209-mcp (2 stars, last pushed 22d ago), licensed MIT. It adds 91 tokens to every session and 6,422 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…