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 psp-solar-wind-switchbacksgit 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/psp-solar-wind-switchbacks)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/psp-solar-wind-switchbacks"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/psp-solar-wind-switchbacks.svg" alt="Measured on agentmods" 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 | $0.02630 |
| Opus 5 | $0.00028 | $0.01315 |
| Sonnet 5 | $0.00011 | $0.00526 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
psp-solar-wind-switchbacks 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 8d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PSP solar wind and switchback workflow
Use this skill for Parker Solar Probe (PSP) near-Sun solar-wind papers or event requests involving Encounter 1, switchbacks, structured slow wind, Alfvénic velocity spikes, or magnetic-field rotations. It turns a paper/event prompt into a narrow FIELDS + SWEAP data plan, an artifact bundle, and explicit proxy labels.
Good first targets
| Paper/event family | Typical starting interval | Products | First diagnostic |
|---|---|---|---|
Bale et al. 2019 structured slow wind, DOI 10.1038/s41586-019-1818-7 |
PSP E1, e.g. 2018-11-05/00:00:00–2018-11-07/00:00:00 until the paper figure interval is confirmed |
FIELDS MAG RTN 1-min + SWEAP/SPC L3i | Br/Bt/Bn, ` |
Kasper et al. 2019 Alfvénic velocity spikes, DOI 10.1038/s41586-019-1813-z |
PSP E1 windows around perihelion, e.g. 2018-11-06/00:00:00–12:00:00 |
FIELDS MAG RTN + SWEAP/SPC velocity moments | B/V component rotations, speed spikes, candidate Alfvénic correlation |
Dudok de Wit et al. 2020 switchbacks, DOI 10.3847/1538-4365/ab5853 |
PSP E1 multi-hour to multi-day windows | FIELDS MAG RTN, optional SPC context | deflection-angle histogram, threshold sensitivity, candidate switchback fraction |
Horbury et al. 2020 sharp Alfvénic impulses, DOI 10.3847/1538-4365/ab5b15 |
PSP E1 paper interval or smoke window such as 2018-11-06/00:00:00–06:00:00 |
FIELDS MAG RTN + SWEAP/SPC | matched-cadence B/V rotations, deflection angle, candidate velocity-jump/Alfvénicity proxy |
Chhiber et al. 2020 PVI/intermittent structures, DOI 10.3847/1538-4365/ab53d2 |
PSP E1 short windows around perihelion, e.g. 2018-11-06/00:00:00–03:00:00 for cache-friendly smoke |
FIELDS MAG RTN, optional SWEAP/SPC context | PVI by explicit lag, thresholded intermittent-structure candidates, event table |
PSP E1 turbulence / cascade papers, DOIs 10.3847/1538-4365/ab60a3 and 10.3847/1538-4365/ab5dae |
PSP E1 statistically quiet sub-intervals; keep smoke windows narrow until paper windows are confirmed | FIELDS MAG RTN + SWEAP/SPC, preferably high cadence for real analysis | PSD/PVI/increment breadcrumbs first; escalate to solar-wind-turbulence-spectrum or a documented cascade workflow |
Solar Orbiter first results: magnetic switchbacks, DOI 10.1051/0004-6361/202140972 |
June 2020 SolO MAG smoke intervals; verify exact figure intervals before science claims | Solar Orbiter MAG rtn-normal (B_RTN), optional SWA/PAS when available |
MAG-only switchback/deflection panels with explicit SWA fallback caveat |
PSP/Solar Orbiter radial-alignment switchback or stream-interaction papers, DOI 10.1051/0004-6361/202140570 |
2020-09-24–2020-10-02 reduced in-situ window | PSP FIELDS/SWEAP + SolO MAG + optional OMNI | in-situ-first comparison; use spice-conjunction-finder for geometry/context before source mapping |
Solar-source switchback studies, DOI 10.1007/s11207-022-02022-4 |
2020-09-27 PSP/SolO smoke intervals before remote-sensing attribution | PSP/SolO in-situ first, remote-sensing only with explicit caveats | separate switchback detection from solar-source attribution and magnetic mapping |
Magnetic field line switchbacks near the Sun, DOI 10.3847/1538-4365/ab4da7 |
PSP E1 perihelion windows such as 2018-11-05/00:00:00–06:00:00 for smoke |
FIELDS MAG RTN + SWEAP/SPC | field-line polarity/deflection proxy, speed overlay, threshold-sensitivity follow-up |
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.
- 8d ago First seen · 148 lines · 57 tokens per session scan A f0d3df2daf08
psp-solar-wind-switchbacks 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 2,630 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…
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…