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 solar-wind-icme-stormgit 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/solar-wind-icme-storm)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/solar-wind-icme-storm"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/solar-wind-icme-storm/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/solar-wind-icme-storm"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/solar-wind-icme-storm.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 | $0.00047 | $0.02274 |
| Opus 5 | $0.00023 | $0.01137 |
| Sonnet 5 | $0.00009 | $0.00455 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
solar-wind-icme-storm 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solar-wind storm and ICME workflow
Use this skill for near-Earth or heliospheric solar-wind event papers: extreme
speed streams, shocks, ICMEs, magnetic clouds, geomagnetic storms, and STEREO
in-situ event reproductions. It complements paper-reproduction with a standard
OMNI/Wind/ACE/STEREO data route and overview panel set.
Good first targets
| Paper/event family | Typical starting interval | Data route | First diagnostic |
|---|---|---|---|
Skoug et al. 2004 Halloween high-speed solar wind, DOI 10.1029/2004JA010494 |
2003-10-29/00:00:00–2003-10-31/00:00:00 |
OMNI HRO 1-min plus Wind/ACE context when needed | speed, Bz GSM, density, temperature, dynamic pressure, SYM-H/AE |
Liu et al. 2014 July 2012 extreme ICME, DOI 10.1038/ncomms4481 |
2012-07-23/00:00:00–2012-07-25/00:00:00 |
STEREO-A MAG + PLASTIC | ` |
Rouillard et al. 2009 Sun-to-Venus storm, DOI 10.1029/2008JA014034 |
2007-11-14/00:00:00–2007-11-21/00:00:00 |
STEREO-A/B MAG 1min + PLASTIC first; SECCHI/J-map and VEX/MESSENGER only as caveated context |
multi-spacecraft in-situ overview, data-volume guardrails, remote-sensing/non-SPEDAS caveats |
| Bastille Day / other Wind-ACE clouds | paper interval or event-list interval | Wind/ACE MFI/SWE plus OMNI for geomagnetic response | shock/sheath/cloud overview with source-specific timing caveats |
Treat event windows as starting points. Exact shock, sheath, ejecta, or magnetic cloud boundaries require paper/event-list confirmation.
Workflow
- Use paper reproduction as the outer contract. For DOI/figure requests, load
paper-reproduction; use this skill for event-product choices and standard panels. - Pick the event frame. Decide whether the reproduction is near-Earth propagated context (usually OMNI), source-spacecraft context (Wind/ACE), or heliospheric context (STEREO/PSP/Solar Orbiter). Record this choice.
- Normalize common variable aliases. Examples seen in real reproductions:
- OMNI geomagnetic indices:
AE_INDEX,AL_INDEX,AU_INDEX,SYM_H; - OMNI solar wind:
flow_speed,proton_density,T,Pressure,BZ_GSM; - STEREO/PLASTIC:
proton_bulk_speed,proton_number_density,proton_temperature; - STEREO/MAG may expose generic
BFIELD; record coordinate/component metadata or keep labels generic if metadata is not surfaced.
- OMNI geomagnetic indices:
- Make a standard overview first. Preferred panels:
- solar-wind speed;
- B components or Bz GSM and
|B|; - proton density;
- proton temperature or thermal speed;
- dynamic pressure when available;
- geomagnetic response (
SYM_H, AE/AL/AU) for near-Earth events.
- Label quality. Use
paper_qualityonly when timing, source, propagation, coordinate basis, and boundary definitions match the paper. Otherwise usecandidate_intervalorproxy. - Record reusable event feedback. If manual code was needed, name the missing preset/alias/overview capability rather than only the single paper.
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 · 154 lines · 47 tokens per session scan A 8c29c485669c
solar-wind-icme-storm is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 2,274 once invoked, about $0.0002 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…