feat(runneth-default): install core skills under /agent/brain/skills - #167
Open
rezakhadjavi wants to merge 5 commits into
Open
Conversation
…nstead of .agents path
…nt/brain/skills paths as discovery backup
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Stacks on top of #141. Changes where the
runneth-defaultpackage stages the three core creative skills.Before:
agent_skillsroot ->/agent/.agents/skills/<name>/SKILL.mdAfter:
agent_brainroot,skills/<name>path ->/agent/brain/skills/<name>/SKILL.mdanalyzing,briefing,creative-generationnow install into a dedicatedskills/folder under brain.core-creative-skillspackage_instruction resource is unchanged (instructions still live in the fixed package instruction path).Heads-up (the "any issues?" part)
Skills auto-register/auto-invoke only when they live in
/agent/.agents/skills/(or a loaded context layer points at their path). Moving them to/agent/brain/skills/means they become plain files on disk, not auto-loaded skills. The package_instruction currently only lists the skill names, not paths, so as-is the agent will know the names but not where to read them. If auto-discovery from brain is desired, the instruction file (or a loaded layer) should reference the/agent/brain/skills/<name>path.Validation
node --test scripts/validate-runneth-package-index.mjs—agent_brainis an approved target root; relative pathskills/<name>passes.