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 erg-arase-radiation-belt-wavesgit 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/erg-arase-radiation-belt-waves)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/erg-arase-radiation-belt-waves"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/erg-arase-radiation-belt-waves/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/erg-arase-radiation-belt-waves"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/erg-arase-radiation-belt-waves.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 | $0.00146 | $0.02747 |
| Opus 5 | $0.00073 | $0.01373 |
| Sonnet 5 | $0.00029 | $0.00549 |
| Haiku 4.5 | $0.00015 | $0.00275 |
Grade A, and why
erg-arase-radiation-belt-waves 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ERG/Arase radiation-belt, wave-particle, and ground-conjugate workflows
Use this skill when the science request mentions ERG, Arase, PWE/OFA/HFA, MGF, MEP-e/HEP/XEP/LEP, chorus/EMIC/hiss/whistler waves, radiation-belt electron flux, pulsating aurora, ISEE/MAGDAS/STEL ground magnetometers, OMTI all-sky imagers, VLF, or ground-conjugate context.
This is a route-scout skill, not a new analysis implementation. It tells an agent where the data usually lives, what the first artifact should be, and where the paper-quality boundary is. Keep all outputs artifact-first: write run metadata, provenance, variable lists, plots, and any diagnostics to the output directory; return only compact paths and caveats.
Route map
MCP/default-surface boundary
Read the table MCP-first. When a row lists a CDAWeb dataset, use the Agent Kit MCP
unified data tools (browse_data_sources, load_data_source,
browse_data_parameters, fetch_data_product) against that dataset before
falling back to local Python. The pyspedas.erg.* names are external runtime
routes, not Agent Kit MCP tools (external_runtime_route.not_an_mcp_tool: true).
Ground-conjugate rows without a packaged CDAWeb dataset are PySPEDAS-only: an
MCP-only client should preserve them as caveats/next-step routes and should not
invent dataset IDs or MCP tool names.
| Research intent | Route to try | Products / variable families | First artifact |
|---|---|---|---|
| Arase magnetic field context | pyspedas.erg.mgf(...) or CDAWeb ERG_MGF_L2_8SEC |
erg_mgf_l2_mag_8sec_* (often GSM/GSE components) |
B-field overview plus coordinate/frame note |
| PWE/OFA wave spectra (chorus/EMIC/hiss/whistler context) | pyspedas.erg.pwe_ofa(...) or CDAWeb ERG_PWE_OFA_L2_SPEC |
erg_pwe_ofa_l2_spec_E_spectra_*, erg_pwe_ofa_l2_spec_B_spectra_* |
E/B spectrogram quick-look; then load wave-polarization for real mode work |
| PWE/HFA upper-hybrid or electron-density route scout | pyspedas.erg.pwe_hfa(...) or CDAWeb ERG_PWE_HFA_L2_SPEC_HIGH/LOW/MONIT |
HFA high/low/monitor spectra, frequency axes, support variables | HFA spectrogram + frequency-axis metadata; do not claim derived density yet |
| Electric-field / waveform context | pyspedas.erg.pwe_efd(...), pwe_wfc(...) |
EFD potential/electric field, waveform products when available | variable inventory and narrow-window plot |
| Electron flux / radiation-belt browse | pyspedas.erg.mepe(...), hep(...), xep(...), lepe(...); CDAWeb ERG_MEPE_L2_OMNIFLUX, ERG_HEP_L2_OMNIFLUX, ERG_XEP_L2_OMNIFLUX, ERG_LEPE_L2_OMNIFLUX |
erg_*_l2_omniflux_*, 3D flux products where available |
energy-channel/units table plus flux overview; do not infer PSD or loss cone |
| Ion flux / ring-current context | pyspedas.erg.mepi_nml(...), mepi_tof(...), lepi(...); CDAWeb ERG_MEPI_L2_OMNIFLUX, ERG_MEPI_L2_3DFLUX, ERG_LEPI_L2_OMNIFLUX |
ion omniflux/3D flux products | energy/species table plus flux overview |
| Orbit / attitude / conjunction context | pyspedas.erg.orb(...), att(...); CDAWeb ERG_ORB_L2 |
erg_orb_l2_pos_gsm, attitude/support variables |
orbit plot + frame/provenance record; load field-line-footpoint for mapping |
| Ground magnetometer context | pyspedas.erg.gmag_isee_fluxgate(...), gmag_isee_induction(...), gmag_magdas_1sec(...), gmag_mm210(...), gmag_stel_fluxgate(...), gmag_stel_induction(...) |
site/cadence-selected ground variables | station/cadence availability diagnostics + ground trace plot |
| Ground optical context | pyspedas.erg.camera_omti_asi(...) |
omti_asi_<site>_<wavelength>_image_raw (for example ath_5577) |
image-shape preview, station/filter metadata, compact sample frame |
| VLF / SuperDARN / other ground context | pyspedas.erg.isee_vlf(...), sd_fit(...) |
site-selected VLF/radar products | route diagnostic + provenance; avoid mapping claims without geometry |
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 · 138 lines · 146 tokens per session scan A 899d6cdfc2f2
erg-arase-radiation-belt-waves is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 2,747 once invoked, about $0.0007 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…