sighttrue.com

Call this before adding a dependency.

Read the current standing of one open-source package: downloads with the window they cover, OpenSSF scorecard, advisory count, licence, whether the repository is archived, and when it was last pushed to.

Read a whole dependency list at once and report what is archived, what carries advisories, what has a source-available licence, and what has not been pushed to in a year.

Find watched repositories whose name contains a string, with their current readings.

Hold two watched repositories against each other across downloads, OpenSSF scorecard, advisories, forks, stars and findings on record.

Find language models by price and context window, from a catalogue read daily across sixty providers.

Check whether a runtime, database or framework release is still receiving security fixes, and what to move to.

Recorded incidents for a hosting or API provider over a window, kept after the provider’s own status page dropped them.

List every reading this server can return, what each one measures, and which require a key.

How many accounts hold publish rights on a package, as the registry lists them.

How the published artefact size has moved over time.

Packages whose own publisher has withdrawn them and which are still being installed heavily, with the download figure and the publisher’s notice.

Whether a name is one edit away from a more widely installed package.

Packages that ask for funding, beside how heavily they are installed and how many people write them.

Days between an advisory being published and a release appearing that postdates it, per package and as a distribution.

Advisories broken down by severity rather than counted, with identifiers and dates.

Support end dates for the runtimes a dependency set requires, including any already past.

For a container base image: its size, when it was last rebuilt, and whether the OS underneath it is still supported.

Recorded outages of the package registries themselves, kept after their status pages drop them.

A provider’s recorded incidents, grouped by the component that failed, over the whole archive rather than the window its status page shows.

How long a provider takes to acknowledge an incident: the interval between an incident starting and its first public update.

When a provider last changed its terms or pricing page, from a stored fingerprint of the page.

Every recorded price for a model, with the date each was read.

Models that were in the catalogue and no longer are, with the date last seen.

For a technology tag: questions asked against questions answered, over time.

Read a whole manifest and return every reading on record for it, ordered by how much a reviewer would want to know.

What changed for a set of packages since a given date, read from the daily archive.

Add a package to the caller’s own private watchlist, so later readings are about their stack rather than the public one.

Everything that has changed across the caller’s private watchlist since a given date: withdrawals, licence changes, advisories, archived repositories and runtimes going out of support.

Given a finding id, return what was measured, when, by whom, and the address it can be checked at.

Whether the domains a package points at — homepage, funding, documentation — still resolve to a registered owner.