# Know what a package will run before it is installed

> Know what a package will run before it is installed: 0 companies fully do it, 0 with a limit, 1 carry the tag. Every listing in Agent package managers with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/agent-packages.vet-before-install/
- Markdown: https://www.anchorterminal.com/niches/agent-packages.vet-before-install/index.md (~650 tokens)
- Slim: https://www.anchorterminal.com/niches/agent-packages.vet-before-install/index.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/agent-packages.vet-before-install/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

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

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 0 | 0 | 1 | 13 | 5 |

## What counts as done

The tool states what runs at add, sync and launch (scripts, hooks, MCP servers started), lists them for the package before install, asks or refuses before running any, and never reads credentials such as gh or env tokens without saying so. Hooks and MCP servers added by an update are shown as a change.

How agents ask for it: is this skill safe to install; what does this plugin run on install; scan the skills we use; don't let it read my tokens

- not this job: Agentpack (No legal entity found. The licence reads Copyright (c) olegpustovit and contributors, and the docs name Oleg Pustovit as author): Docs say no npm package script runs when a locked MCP tree is unpacked and that the gh token is read, but nothing lists a package's hooks and MCP servers before install or asks before staging them; the integrity page tells users to vet content themselves.

## What stops agents finishing

- registries with a measurable share of malicious skills
- the CLI reads the user's GitHub token at add time
- setup phases that install dependencies with the developer's access
- no advisory process or security contact for the tool itself

## Around it

Before: search.specialist-sources. After: agent-packages.install-package.

## Where this comes from

Weight 13 of 100 in Agent package managers: 4 of 31 accounts have this as their main job (share 12.9, rounded by largest remainder to sum 100)

As data: https://www.anchorterminal.com/api/v1/use-cases/agent-packages.vet-before-install.json, or the MCP tool get_use_case with id agent-packages.vet-before-install. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
