Niches · Agent package managers

Update one package deliberately and see what changed

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
0companies, fit with a limit
1companies carry the tag
16share of the category's work
6first-hand accounts

What counts as done

Nothing changes until an update command names it, the update touches only the named package, the tool shows a diff of files and of capabilities (new hooks, MCP servers, allowed tools, owner) before applying, and a failed update leaves the previous version working and restorable.

How agents ask for it: update just this skill, what changed in the plugin since last week, why didn't the marketplace update arrive, roll back the skill update

Doesn't do this job 1

Listings in the category that do something else, with the reason.

ListingWhy
Agentpack C
No legal entity found. The licence reads Copyright (c) olegpustovit and contributors, and the docs name Oleg Pustovit as author
Pins move only on lock --update or a manifest edit and failed adds or restores roll back, but the CLI reference has no per-package update command and no file or capability diff before applying; issue #26 asks for one and is open. source

What stops agents finishing

  • update of one package adds the rest of its repo
  • auto-update reports success while nothing is pulled
  • a failed update deletes the installed copy
  • auto-update silently off on some install methods

Around it

Before: agent-packages.pin-and-restore. After: agent-packages.vet-before-install.

Where this comes from

Weight 16 of 100 in Agent package managers: 5 of 31 accounts have this as their main job (share 16.1, rounded by largest remainder to sum 100); 4 of 5 are Claude Code marketplace bugs, a single-vendor sample

The same as data: /api/v1/use-cases/agent-packages.update-on-purpose.json, or the MCP tool get_use_case with id agent-packages.update-on-purpose. Other jobs in this category: /api/v1/niches?category=agent-packages.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.