Niches · Agent package managers
Give several coding agents the same skills, plugins and MCP servers
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
Each named agent gets the same content in its native layout, a skill with the same name in two sources resolves the same way in every agent or the tool reports the clash, and nothing is written outside the paths the tool owns. The docs list the agents supported and which asset types each receives.
How agents ask for it: make Codex use the same skills as Claude Code
, add this MCP server to Cursor and Claude too
, stop me editing four config files
, why does Cursor behave differently from Claude here
Does the job, with a limit 1
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Agentpack C No legal entity found. The licence reads Copyright (c) olegpustovit and contributors, and the docs name Oleg Pustovit as author | Seven launchers with a per-agent table of what is staged where. Gemini CLI and Copilot CLI are unsupported (#27), a same-name skill resolves differently per agent with no diagnostic (#12), and Codex sync writes to the real HOME and leaves files after remove (#14). source |
What stops agents finishing
- an agent the team uses is not supported
- asset types (hooks, permissions, MCP) staged for some agents only
- same-name resolution differs per agent with no diagnostic
- sync writes into the real home folder or leaves files after remove
Around it
Before: agent-packages.install-package. After: agent-harnesses.pair-in-terminal.
Where this comes from
Weight 19 of 100 in Agent package managers: 6 of 31 accounts have this as their main job (share 19.4, rounded by largest remainder to sum 100); 3 are Agentpack's own maintainer issues
The same as data: /api/v1/use-cases/agent-packages.sync-across-agents.json, or the MCP tool get_use_case with id agent-packages.sync-across-agents. Other jobs in this category: /api/v1/niches?category=agent-packages.
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.