feat: Add agent teams support for parallel skill execution#4
Open
lmiccini wants to merge 3 commits into
Open
Conversation
Add experimental agent teams support enabling parallel execution across four skills: /code-review (3 parallel reviewers), /feature (3 parallel researchers), /task-executor (parallel task groups in worktrees), and /debug-operator (parallel hypothesis testing). New team-role agents: researcher (read-only analysis), implementer (write-capable task execution), and reviewer (focused code review with cross-validation). All skills gracefully fall back to sequential behavior when CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is not enabled. Includes shared infrastructure (lib/team-helpers.sh), 44 new tests (tests/test-teams.sh), CI integration, and design documentation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a 4th researcher teammate to /feature parallel research that challenges the other researchers' findings. The devil's advocate spawns after the initial 3 researchers report, receives all findings, and critiques them for unsupported assumptions, missed alternatives, risks, and convention gaps. Valid concerns are incorporated as risks in the implementation strategies. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Luca Miccini <lmiccini@redhat.com>
2e6fcfb to
9caf106
Compare
New agent-backed skill for writing tobiko tests, AnsibleTest playbooks, and generating test-operator CRs (Tempest, Tobiko, AnsibleTest, HorizonTest). The agent encodes deep domain knowledge including CRD schemas, tobiko fixture patterns, and the iha-tests playbook convention. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Luca Miccini <lmiccini@redhat.com>
9caf106 to
46ac4e0
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
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.
Add experimental agent teams support enabling parallel execution across four skills: /code-review (3 parallel reviewers), /feature (3 parallel researchers), /task-executor (parallel task groups in worktrees), and /debug-operator (parallel hypothesis testing).
New team-role agents: researcher (read-only analysis), implementer (write-capable task execution), and reviewer (focused code review with cross-validation). All skills gracefully fall back to sequential behavior when CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is not enabled.
Includes shared infrastructure (lib/team-helpers.sh), 44 new tests (tests/test-teams.sh), CI integration, and design documentation.