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 spedas-skills-indexgit 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/spedas-skills-index)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/spedas-skills-index"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/spedas-skills-index/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/spedas-skills-index"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/spedas-skills-index.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 | $0.00057 | $0.02417 |
| Opus 5 | $0.00028 | $0.01208 |
| Sonnet 5 | $0.00011 | $0.00483 |
| Haiku 4.5 | $0.00006 | $0.00242 |
Grade A, and why
spedas-skills-index 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 10d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SPEDAS skills index
The spedas MCP server advertises many tools, but you should not learn them all.
The agent-facing surface is: a small unified vocabulary + these skills. Pick the
skill matching the intent, load it, follow it. Call spedas_overview() if unsure what
exists; treat the full tool list as discoverable on demand, not memorized.
The unified vocabulary (what skills compose)
- Plan:
search_spedas_data_sources,plan_spedas_observation,compare_cdaweb_pds_spice,create_spedas_analysis_bundle - Data (one set of verbs, switch by
source_type=cdaweb|pds|spice):browse_data_sources,load_data_source,browse_data_parameters,fetch_data_product,manage_data_cache - Geometry:
get_ephemeris,compute_distance,transform_coordinates - Analysis (
[analysis]extra): coordinate transforms, spectra, field models, particle moments,render_tplot
Low-level / source-specific compat tools exist for maintenance only — skills do not use them.
Intent → skill → first step
| If the user wants… | Use skill | First call |
|---|---|---|
| Reproduce a published paper, figure, event, or DOI with artifact/provenance output | paper-reproduction |
spedas_overview then search_spedas_data_sources / plan_spedas_observation |
| PSP/Solar Orbiter heliospheric load-plan bridge, FIELDS/SWEAP/SolO MAG/SWA/RPW/EPD product selection, radial-alignment route scout, or inner-heliosphere in-situ comparison | psp-solo-heliophysics-workflows |
spedas_overview then search_spedas_data_sources / plan_spedas_observation; load spice-conjunction-finder when geometry matters |
| Parker Solar Probe / Solar Orbiter switchbacks, Alfvénic impulses, or radial-alignment in-situ comparisons | psp-solar-wind-switchbacks |
spedas_overview then search_spedas_data_sources / plan_spedas_observation; load spice-conjunction-finder when geometry matters |
| Solar-wind storm, ICME, magnetic cloud, stream interaction, SEP reduced proxy, or multi-spacecraft in-situ overview (OMNI/Wind/ACE/STEREO/PSP/SolO) | solar-wind-icme-storm |
spedas_overview then search_spedas_data_sources / plan_spedas_observation; compose scalar OMNI vectors, start STEREO multi-day runs at 1-minute cadence, and keep SEP onset/fluence claims gated on channel metadata |
| The turbulence/wave power spectrum of a field interval | solar-wind-turbulence-spectrum |
create_spedas_analysis_bundle |
| Solar-wind intermittency, PVI, vector increments, thresholded event tables, or proxy-labelled energy-transfer / third-order-law workflow | solar-wind-turbulence-intermittency |
create_spedas_analysis_bundle |
Wave polarization (whistler/EMIC/chorus: degpol, wave-normal angle, ellipticity; THEMIS SCM scf/scp/scw valid-window checks) |
wave-polarization |
create_spedas_analysis_bundle |
| A boundary normal / LMN frame for a crossing | boundary-minimum-variance |
create_spedas_analysis_bundle |
| Hodogram: vector component-vs-component for wave polarization / rotation sense (LMN) | hodogram |
create_spedas_analysis_bundle |
| Apply a FAC/LMN/rotation matrix to a vector series | apply-rotation-matrix |
(matrix from generate_fac_matrix / MVA) |
Translate PySPEDAS/IDL cotrans, FAC/MVA/LMN, or tplot coordinate metadata into the right Agent Kit transform route |
coordinate-transform-recipes |
create_spedas_analysis_bundle |
| Four-spacecraft curlometer J, linear B gradients/curvature, or magnetic nulls | multi-spacecraft-gradients |
create_spedas_analysis_bundle |
| Cluster/Geotail/THEMIS magnetotail boundary, current-sheet, or multi-spacecraft proxy/scouting overview | spedas-workflow + multi-spacecraft-gradients |
search_spedas_data_sources; use docs/examples/cluster_geotail_themis_magnetotail_multispacecraft.md, keep single_spacecraft_cis / fgm_route_empty and not_paper_exact labels, and require four-spacecraft FGM + positions before curlometer/timing claims |
| A full magnetopause/bow-shock crossing study (B + plasma + position) | magnetopause-lmn-analysis |
search_spedas_data_sources |
| Times two spacecraft/bodies are close | spice-conjunction-finder |
spedas_overview then manage_data_cache(source_type="spice", action="status") |
| Distance from a spacecraft to the magnetotail neutral sheet | neutral-sheet-distance |
create_spedas_analysis_bundle |
| Model (Shue) LMN boundary-normal frame for a magnetopause crossing | model-lmn-boundary |
create_spedas_analysis_bundle |
| Clean/condition a messy time-series before analysis (despike, deflag, smooth, gap-fill) | timeseries-cleaning |
create_spedas_analysis_bundle |
| Build or validate a 3D particle distribution artifact for moments, spectra, PAD, or velocity-space slices | particle-distribution-recipes |
create_spedas_analysis_bundle; [analysis] build_particle_distribution_artifact / load_particle_distribution_artifact when enabled |
| 2D velocity-space slice of a particle distribution (beams/crescents) | particle-velocity-slice |
create_spedas_analysis_bundle |
| Just fetch & plot a time series | spedas-workflow |
plan_spedas_observation |
| ERG/Arase radiation-belt, wave-particle, PWE/MGF/particle, or ground-conjugate ISEE/OMTI/MAGDAS route scout | erg-arase-radiation-belt-waves |
spedas_overview; use this skill to choose pyspedas.erg.* / CDAWeb satellite routes, and keep ground routes labeled PySPEDAS-only |
| Standard mission overview plot, geomagnetic-index context, GOES XRS operational storm context, THEMIS FGM/ESA substorm/dipolarization proxy, or RBSP MagEIS/REPT radiation-belt overview | overview-geomagnetic-indices |
spedas_overview |
| THEMIS mission route scout, substorm/dipolarization context, magnetotail boundary preflight, or FGM/state/ESA/SST/SCM workflow planning | themis-workflows |
create_spedas_analysis_bundle then spedas_overview / search_spedas_data_sources |
| MMS FGM/MEC/EDP/SCM/FPI/HPCA quicklook, reconnection route scout, product-selection workflow, particle/PAD preflight, or curlometer/linear-gradient readiness check | mms-basic-workflows |
create_spedas_analysis_bundle then spedas_overview / search_spedas_data_sources |
| Lightweight OMNI/Kyoto/NOAA space-weather smoke workflow, storm-context bundle, or cache-only geomagnetic-index validation | omni-kyoto-noaa-smoke-workflows |
create_spedas_analysis_bundle then spedas_overview / overview-geomagnetic-indices |
| To know what data/sources exist at all | spedas-workflow |
spedas_overview |
Plan a PySPEDAS mission/product/time data load with time_clip=True, cache, downloadonly, notplot, and provenance hygiene |
pyspedas-load-planning |
create_spedas_analysis_bundle |
| Manage tplot variables from load through inspect, derive, plot/export, and cleanup without raw-array chat output | tplot-data-lifecycle |
create_spedas_analysis_bundle |
| Choose PyTplot/SPEDAS plotting options for line plots, spectrograms, legends, limits, event bars, annotations, and saved figure artifacts | pytplot-plotting-options |
create_spedas_analysis_bundle; use [analysis] render_tplot only when that extra is enabled |
Translate IDL SPEDAS / PySPEDAS / plugin vocabulary into Agent Kit skills/resources while marking external routines as not_an_mcp_tool |
spedas-heritage-vocabulary |
spedas_overview |
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.
- 10d ago First seen · 75 lines · 57 tokens per session scan A 24d2e0a8d8d6
spedas-skills-index is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,417 once invoked, about $0.0003 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…
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.
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…
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…