feat(teams): add agent team support with subagent definitions and skill migrations#55
Open
wpfleger96 wants to merge 1 commit into
Open
feat(teams): add agent team support with subagent definitions and skill migrations#55wpfleger96 wants to merge 1 commit into
wpfleger96 wants to merge 1 commit into
Conversation
Agent role definitions (security-reviewer, perf-reviewer, impl-worker, etc.) now live in a generic src/ai_rules/config/agents/ directory and get distributed to both Claude Code (~/.claude/agents/) and Gemini CLI (~/.gemini/agents/) via the SharedAgent symlink infrastructure — same pattern skills already use. This replaces the prior Claude-only approach (src/ai_rules/config/claude/agents/) with a portable-first design. Skills keep their existing Agent-tool orchestration as primary, with a minimal conditional hint for teams optimization when available.
wpfleger96
force-pushed
the
feat/agent-teams
branch
from
a78edb1 to
a07db7a
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds Claude Code agent team support — a library of 7 subagent role definitions and migrations of
/researchand/code-reviewerto use native teams instead of ad-hocAgentspawning.Claude Code's experimental agent teams feature allows spawning coordinated teammates with shared task lists and peer-to-peer messaging. The version-controllable primitive is subagent definitions (
.claude/agents/*.md), which ai-rules already symlinks fromsrc/ai_rules/config/claude/agents/— the directory just needed to be created and populated. Teams are gated to the personal profile so default-profile users don't get the experimental feature;workinherits it viaextends: personal.src/ai_rules/config/claude/agents/— 7 role definitions symlinked to~/.claude/agents/:security-reviewer(opus),perf-reviewer,test-coverage-reviewer,impl-worker(worktree-isolated),test-writer-agent,researcher, andresearch-synthesizer/researchStandard+ tiers migrated toTeamCreate+TaskCreatewithresearcherandresearch-synthesizerteammates; lead reviews synthesizer output before delivery; falls back to parallelAgentcalls when teams unavailable/code-reviewerMedium/Large path migrated: lead handles Design & Functionality inline whilesecurity-reviewer,test-coverage-reviewer, and optionallyperf-reviewerrun as teammates; crossfire path unchangedCLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1added topersonal.yamlundersettings_overrides.claude.env;workprofile inherits viaextends: personal