virtual-team
CLAUDE.md14 starsChanged 8 months agoMITView on GitHub
This is a multi-host development-agent plugin for Claude Code and Codex. It provides a virtual development team workflow: TDD, debugging, code review, backlog management, and proven workflow patterns. Validates frontmatter, file references, and command references across all markdown files.
In this repository50 other files it gives its agents.
- adr-conventionSkill
- architecture-vocabularySkill
- backlog-externalSkill
- backlog-localSkill
- backlogSkill
- checkpointsSkill
- design-principlesSkill
- domain-glossarySkill
- git-practicesSkill
- grounded-claimsSkill
- knowledge-checkSkill
- policy-riskSkill
- positive-framingSkill
- receiving-code-reviewSkill
- skill-authoringSkill
- skill-awarenessSkill
- subagent-driven-developmentSkill
- test-driven-developmentSkill
- token-efficientSkill
- triageSkill
- verification-before-completionSkill
- workflow-bugSkill
- workflow-checkSkill
- workflow-commitSkill
- workflow-contractsSkill
- workflow-debugSkill
- workflow-decisionsSkill
- workflow-docsSkill
- workflow-doctorSkill
- workflow-epicSkill
- workflow-featureSkill
- workflow-flow-fix-pipelineSkill
- workflow-flowSkill
- workflow-grillSkill
- workflow-handoffSkill
- workflow-ideaSkill
- workflow-implementSkill
- workflow-planSkill
- workflow-proposalSkill
- workflow-prSkill
- workflow-refineSkill
- workflow-researchSkill
- workflow-reviewSkill
- workflow-startSkill
- workflow-statusSkill
- workflow-tech-reviewSkill
- workflow-update-workflowSkill
- workflow-validateSkill
- workflow-worktreeSkill
- workflow-yoloSkill
The file
Files
Virtual Team Plugin — Contributor Guide
This is a multi-host development-agent plugin for Claude Code and Codex. It provides a virtual development team workflow: TDD, debugging, code review, backlog management, and proven workflow patterns.
Repository Structure
commands/ — Slash commands (/flow, /implement, /commit, etc.)
skills/ — Skills loaded by commands (TDD, git-practices, etc.)
agents/ — Specialized sub-agents (pattern-finder, security-reviewer, etc.)
hooks/ — Platform hook scripts (session-start, run-hook.cmd)
examples/ — Example CLAUDE.md templates and stack-specific skills
tests/ — Static validation tests (frontmatter, refs, commands)
.claude-plugin/ — Claude Code plugin manifest
.codex-plugin/ — Codex plugin manifest
.codex/ — Codex installation and migration instructions
skills/workflow-* — Thin Codex workflow adapters that load canonical commands
.cursor-plugin/ — Cursor plugin manifest
.opencode/ — OpenCode plugin adapter
.codex/ — Codex installation instructionsConventions
- Commands, skills, agents, and Codex workflow adapters use YAML frontmatter with
nameanddescriptionfields - Command names match their filename (kebab-case)
- Skills live in
skills/<name>/SKILL.md - Cross-references use root-relative paths (e.g.,
skills/git-practices/SKILL.md, not.claude/skills/...) - The bootstrap skill is
virtual-team:skill-awareness— it loads via SessionStart hook - Files under
commands/are canonical workflow specifications. Codex adapters must reference them rather than duplicate their bodies. - Host-specific invocation and tool differences belong in
skills/codex-host-adaptation.md, not in canonical workflow files. - For detailed skill authoring rules (size budget, descriptions, reference files, review checklist), see
skills/skill-authoring/SKILL.md
Testing
npm testValidates frontmatter, file references, and command references across all markdown files.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

