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 paper-reproductiongit 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/paper-reproduction)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/paper-reproduction"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/paper-reproduction/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/paper-reproduction"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/paper-reproduction.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 | $0.00042 | $0.01507 |
| Opus 5 | $0.00021 | $0.00754 |
| Sonnet 5 | $0.00008 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
paper-reproduction 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 9d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper reproduction workflow
Use this skill when a researcher asks to reproduce, sanity-check, or extend a published paper, figure, event list, or DOI using SPEDAS / PySPEDAS / Agent Kit. The goal is not to claim a paper-quality reproduction on the first pass. The goal is to make a narrow, auditable researcher attempt that produces artifacts, records provenance, and turns every missing capability into concrete Agent Kit feedback.
Deliverables
Write an artifact bundle under an explicit output_dir containing at least:
REPORT.md— citation, science question, interval/product assumptions, reproduction status, caveats, and Agent Kit feedback.artifacts/provenance.json— machine-readable run record using the schema below.- One or more plots or small derived tables. Prefer PNG/HTML/JSON artifacts over pasted arrays or CDF contents.
- The script, notebook, or recipe that regenerated the artifacts.
Workflow
- Intake the paper evidence. Capture title, DOI, figure/table target, science
question, mission(s), instrument(s), cadence, coordinate basis, and any exact
interval from the paper or supplement. If the interval is inferred, label it as
candidate_interval. - Plan the data route before fetching. Choose
source_type, dataset/product, parameters/variables, time range, cache/output directory, and expected artifact shape. Start withspedas_overview,search_spedas_data_sources,plan_spedas_observation, orcreate_spedas_analysis_bundlewhen the route is unclear. If you bypass Agent Kit and use PySPEDAS directly, state why. - Fetch narrowly. Use the smallest interval and product set that can test the paper claim. Keep cache and output paths isolated per paper/iteration.
- Reproduce one minimum diagnostic. Make a researcher-useful first plot or
derived quantity before attempting the full paper. Examples: overview time
series,
E + Ve×B/J·E'proxy,E_parallelproxy, PSD, pitch-angle distribution, or particle distribution slice. Label proxy diagnostics asproxy, not paper-quality. - Validate visually and numerically. Check the artifact is non-empty, axes and units are labeled, spikes/features align with the target interval, and the provenance contains enough fields to rerun the attempt.
- Record Agent Kit feedback. For every paper, write one concrete gap or improvement. Batch repeated gaps across several papers before opening PRs; avoid one issue per paper unless the bug blocks progress.
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.
- 9d ago First seen · 162 lines · 42 tokens per session scan A dc93f0153891
paper-reproduction is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,507 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…
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…