Per-agent skill assignment and connector grants

Open
#639 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
48/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
typescript

Research direction

Read governance/tool-policy.ts and the implementation of agent run setup, skill loading, and connector exposure; the issue names no paths for those latter entry points. Trace how tool policies are applied, then define how per-agent grants and assignments feed into each run. Done means ungranted connector tools are hidden and removing an assigned skill prevents it loading on the next run.

Written by the indexing model from the issue text.

Description

Split from #136, whose Outputs, keyed documents, PR links and Skill Studio are done.

Remaining:

  • Assign skills per agent; the agent's runs load only its assigned skills.
  • Connector grants per agent: only granted connectors (MCP servers/tools) are exposed to that agent's runs, building on governance/tool-policy.ts allow/ask/deny.

Acceptance: an agent without the GitHub connector grant cannot see its tools; removing a skill from an agent stops it loading on the next run.

Dominant language
TypeScript
Stars
3
Forks
0
Avg merge
17h 33m
Merged PRs (30d)
163

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from musterhq/muster-code

All issues in musterhq/muster-code

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.