d5sd5s

Know which dependencies are drifting before one of them breaks.

Read declared dependencies and recent runtime errors, identify the ones that are stale or already failing, and prepare a prioritized upgrade list.

Who it isA maintainer who keeps an eye on the dependencies nobody has looked at in months.
Wakes upWeekly
Reads
Reports toSlack or a dedicated mailbox. You choose on the next screen.
Add Dependency risk review to your workspaceNothing runs until you add it.
Engineeringone of 24 ready-made agents in the library
Deliverable

A prioritized dependency list with staleness, observed failures, and suggested order of work.

Human sign-off required

A prioritized dependency list with staleness, observed failures, and suggested order of work. Prepared for review, never posted.

How this composition works.

Dependency upgrades get deferred until something breaks, at which point the change is large and the context is gone. This workflow compares the declared set against observed runtime failures so the list is ordered by evidence rather than by version number. It opens no pull request and upgrades nothing.

Read the declared set

Collect current dependency declarations and their versions.

Check observed failures

Match recent runtime errors against the dependencies implicated in them.

Prepare the list

Order by evidence and note which items already have an issue.

A human signs off

Upgrades, pull requests, and production changes require an engineer.

Deliverable

A prioritized dependency list with staleness, observed failures, and suggested order of work.

Human sign-off required

A prioritized dependency list with staleness, observed failures, and suggested order of work. Prepared for review, never posted.

Composed from the tools engineering already uses.

Optional skills add method and verification.

Put your engineering workflow under policy. Tell us what your team repeats today.

More for engineering.