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 spedas/spedas_agent_kit --skill coordinate-transform-recipesgit clone --depth 1 https://github.com/spedas/spedas_agent_kitWrote 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/spedas/spedas_agent_kit/coordinate-transform-recipes)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/coordinate-transform-recipes"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/coordinate-transform-recipes/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/spedas/spedas_agent_kit/coordinate-transform-recipes"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/coordinate-transform-recipes.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 | $0.00073 | $0.02592 |
| Opus 5.5 | $0.00029 | $0.01037 |
| Sonnet 5.5 | $0.00015 | $0.00518 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
coordinate-transform-recipes 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinate transform recipes: PySPEDAS/IDL cotrans to Agent Kit routes
Use this skill when a prompt mentions PySPEDAS cotrans, IDL SPEDAS cotrans,
THEMIS/MMS coordinate cribs, tplot coordinate metadata, FAC, MVA, LMN, quaternions,
GSE/GSM/GEI/SM/GEO/J2000, or "convert this variable/vector to another frame".
It is a route-scout and provenance checklist, not a new tool: it tells an agent
which existing Agent Kit skill/tool path fits the request and when a PySPEDAS/IDL
routine is only an external runtime route.
MCP/default-surface boundary
When documenting PySPEDAS or IDL coordinate routines, use the structured marker
external_runtime_route.not_an_mcp_tool: true. The following are source evidence
or external runtime routes unless a current Agent Kit MCP tool explicitly exposes
them:
pyspedas.cotrans,pyspedas.cotrans_tools.*,fac_matrix_make,minvar_matrix_make,lmn_matrix_make,tvector_rotate;- IDL
cotrans,spd_cotrans,thm_cotrans,thm_cotrans_lmn,mms_cotrans_lmn,mms_qcotrans, and mission.procoordinate helpers (loadspedas-heritage-vocabularywhen translating legacy examples); - PyTplot state helpers such as
cotrans_get_coord,cotrans_set_coord,store_data,get_data, andtplot_names.
Do not present those names as Agent Kit MCP tools. The MCP-first path is:
spedas-skills-index -> this skill or a focused downstream skill -> existing
planning/data/geometry/analysis tools -> artifact paths + provenance/run.json.
When to use
- "Convert THEMIS/MMS/OMNI position or B from GSE to GSM/SM/GEO/J2000."
- "This IDL crib calls
cotrans/thm_cotrans; how do I do the Agent Kit route?" - "Build FAC for wave polarization or PAD interpretation."
- "Rotate B into MVA/LMN for a boundary crossing, then make a hodogram."
- "Check whether a tplot variable's coordinate metadata makes the requested transform meaningful."
Route table
| User intent | Preferred Agent Kit route | External PySPEDAS/IDL evidence |
|---|---|---|
| Choose a science frame (RTN, GSE/GSM, HEE/HEEQ/HCI, J2000) and transform vectors/time series with Agent Kit geometry | coordinate-frame-tour; use transform_coordinates for a single vector, or transform_timeseries_coordinates(input_file=..., coord_in=..., coord_out=..., output_file=...) for an artifact time series |
PySPEDAS cotrans; IDL cotrans |
| Preserve / inspect loaded tplot variable names, coordinates, units, and suffixes before any transform | tplot-data-lifecycle and pyspedas-load-planning; record coord_in, coord_out, variable name, units, and support-data choices |
cotrans_get_coord, cotrans_set_coord, store_data, get_data |
| FAC matrix for B-aligned wave/PAD context | apply-rotation-matrix after generating or importing the FAC matrix; then compose with wave-polarization or pitch-angle-distribution |
fac_matrix_make, tvector_rotate |
| Data-driven MVA/LMN for a boundary or current sheet | boundary-minimum-variance for the MVA basis; apply-rotation-matrix for an explicit matrix stack; hodogram for rotation sense |
minvar_matrix_make, thm_cotrans_lmn, mms_cotrans_lmn |
| Model magnetopause LMN normal / Shue cross-check | model-lmn-boundary or magnetopause-lmn-analysis |
lmn_matrix_make, gsm2lmn |
| Field-line/footpoint/L-shell mapping | field-line-footpoint; supply positions in GSM kilometers first |
IDL/PySPEDAS coordinate conversion helpers |
| Mission-specific attitude/quaternion transforms | Stay in the mission skill (mms-basic-workflows, themis-workflows, psp-solo-heliophysics-workflows) and record the support data/quaternion source before any transform |
mms_qcotrans, dsl2gse, gse2dsl |
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.
- 1mo ago First seen · 167 lines · 73 tokens per session scan A 68957de2dfb5
coordinate-transform-recipes is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 2,592 once invoked, about $0.0003 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.
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…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports 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…
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
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.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.