Decisions

Why skills are copied, checked and supplied to the harness this way.

How does a skill reach an agent?

lnk agent skill add copies its folder into the agent's skills/, so a skill is a file of the agent's like any other: it moves with the agent, a backup keeps it, and you can edit or delete it there. It's named as its SKILL.md says, as the Agent Skills standard does, and checked before anything is copied: a folder that isn't a skill is refused, saying why.

From a URL

A URL is a git repository, cloned once with your own git into a private folder of the system's, never the agent's, since skills are shared as repositories, GitHub's page of a folder naming one in it.

How it's copied

A copy leaves out links and anything that isn't a file or folder, takes at most 1,000 files, 64 MB and 1,000 folders at most 32 deep, and is put in place by a rename, so a harness never lists a skill half copied.

The harness writes skills/ while skill add runs outside its sandbox, so every file and folder is read and written through its folder's handle without following a link: one swapped in, in the skill or where it's copied to, is refused, and a repository's folder that's a committed link can't lead out of the clone. A harness that doesn't take Link's instructions doesn't read skills/, and skill add says so.

In the prompt

Skills are listed in the prompt whether or not memory is on, so the prompt stays the same across conversations, a narrowed subagent's included. Memory is opt-in, so skill add says when it's off: the one place it's seen.