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 agentlas-ai/agentlas-desktop --skill light-curve-periodicitygit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/light-curve-periodicity)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/light-curve-periodicity"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/light-curve-periodicity/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/agentlas-ai/agentlas-desktop/light-curve-periodicity"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/light-curve-periodicity.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 | $0.00039 | $0.00600 |
| Opus 5.5 | $0.00016 | $0.00240 |
| Sonnet 5.5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
light-curve-periodicity 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 1mo 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Irregular light-curve periodicity
- Bind the exact source file or table SHA-256. Do not copy values from a plot or invent missing observations.
- Confirm the numeric time system and any constant day offset. Never silently treat UTC, TDB, JD, MJD, HJD, or BJD as interchangeable.
- Preserve one stable observation ID, nullable time, nullable value, nullable positive standard error, and the explicit
useflag for every input row. - Choose the period bounds and finite frequency count before calling
analyze_light_curve_periodicity. The grid is linearly spaced in frequency, inclusive, and capped at 5,000 frequencies over at most 2,000 observations. - Prefer
weightedwhen every usable measurement has a defensible standard error. Inweightedmode, otherwise complete rows without an error are excluded rather than imputed.autofalls back to a fully unweighted fit if any otherwise complete row lacks an error. - Interpret
poweras the declared floating-mean GLS standard normalization, not a probability. Inspect the sampling-window curve and cadence warnings before calling a peak astrophysical. - Treat reported peaks as local maxima on the requested grid. The basic tool reports a Baluev analytic false-alarm upper bound and a Montgomery-O'Donoghue period standard-error estimate when numerically resolvable; neither is a calibrated detection probability or confidence interval, and a returned zero is a numerical floor. It does not compute red-noise corrections, detrending, multi-harmonic fits, or transit templates.
- Use
analyze_light_curve_periodicity_depthfor the separately bounded depth pass: seeded permutation-bootstrap FAP, local peak refinement, peak-width/analytic/bootstrap period uncertainty, daily/sidereal alias screening, and a fixed two-harmonic comparison. A zero bootstrap exceedance must be reported with its finite-sample upper bound, not as exact FAP=0. - Use the observation, peak, and periodogram tables as publication payloads. The Vega-Lite output is a FigureSpec until the host renderer and export pipeline separately validate it.
- For magnitudes, the folded panel reverses the value axis.
phase, fitted values, residuals, amplitudes, and offsets are derived model quantities, not new measurements.
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.
- 1mo ago Changed · +1 lines 5ba6e99a9398
- 1mo ago First seen · 21 lines · 39 tokens per session scan A 54dd9c5c2d83
light-curve-periodicity is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 600 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
tbtools
Use when the user asks about TBtools, TBtools-II, TBtools RPC API, TBtools CLI, or bioinformatics operations available through TBtools such as sequence manipulation, BLAST, GFF/GTF/GXF processing, expression tables, heatmaps, trees, MCScanX, DIAMOND, HMMER, MUSCLE, and IQ-TREE.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.
research-orchestrator
Becomes a principal research scientist who orchestrates deep, multi-source research by coordinating evidence gathering, grading source quality, and synthesizing findings with explicit confidence levels. Use when the user needs a comprehensive research report on a complex topic, evidence-based analysis with source…
autoresearch
Run an auto research / autoresearch loop for measurable improvements. Use when optimizing a skill, agent, prompt, code path, benchmark, or other target with a mechanical metric: baseline, mutate one thing, verify, keep or discard, log, chart progress, and optionally save improved custom skills or agents through Open…
architecture-diagram
How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…
scaffold-lean-library
Scaffold a Lean 4 library with Mathlib or PFR, Lake tests, and CI. Use for "new Lean project"; to edit Lean, use write-lean-code.