By bostonaholic
Orchestrates specialized agents to autonomously implement entire features end-to-end
Use when you need to locate files in a codebase relevant to a specific area. Maps conceptual goals to actual file locations even when exact names are unknown. Operates from questions.md only, never the original task description.
Use when an adversarial code review is needed after implementation. Reviews with fresh context and no shared conversation history to prevent self-evaluation bias. Produces a hard-gating verdict — REQUEST CHANGES blocks shipping. Example triggers — "review my changes", "code review the implementation", "check this PR for issues".
Use after research is complete to align with the user on the approach before any code is written. Drafts a ~200-line design document covering current state, desired end state, patterns to follow, decisions made, and explicit open questions for the user. MUST present the open questions interactively before producing the design — replaces the RPI "magic words" problem with structural interaction.
Use when the implementation plan needs to be executed slice by slice. A seasoned coding expert that reads the approved plan, follows TDD discipline, executes one vertical slice at a time, and commits each slice atomically when its tests pass. Dispatched during the Implement phase.
Use after the structure is produced to create the tactical implementation plan. Translates each vertical slice in structure.md into precise file-level steps with acceptance test mappings. The plan is a tactical artifact for the implementer — neither the structure nor the plan is human-reviewed (design is the human gate).
Adversarially review a technical design document with fresh context before the human gate. Dispatches the built-in `general-purpose` subagent (clean context, no shared history with the design-author) against `docs/plans/<id>/design.md` and presents its verdict — APPROVE, REQUEST CHANGES, or COMMENT. Optional, not part of the QRSPI pipeline. Trigger on "review the design doc", "audit design.md", "is this design ready", or `/eng-design-doc-review`.
Engineering standards for design and implementation methodology -- loaded by planner, implementer, and code-reviewer agents for design-first workflow, implementation standards, and quality checklist
Git commit discipline methodology — loaded by the ship phase to produce well-formed commits following conventional commits format, the 50/72 rule, and atomic commit principles
Optional PRD methodology — loaded by the questioner agent when a feature request is vague or complex enough to warrant a structured product spec alongside task.md. Produces a PRD artifact that downstream design-author work can ground decisions in.
Product-need reasoning lens for "make something people want" — loaded by questioner, design-author, and structure-planner to validate user demand while framing, designing, and slicing scope
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A Claude Code plugin that orchestrates specialized agents to autonomously implement entire features end-to-end, driven by the QRSPI workflow. The orchestrator is the main Claude Code session; it persists pipeline state as artifacts in docs/plans/ and tracks live progress with TodoWrite.
📖 Documentation: team.bostonaholic.dev
Each agent does work and returns an artifact. The orchestrator dispatches the next agent based on a phase table. Agents remain decoupled — they know nothing about each other.
QUESTION → RESEARCH → DESIGN → STRUCTURE → PLAN → WORKTREE → IMPLEMENT → PR
task.md) and neutral research questions (questions.md). The questioner is the only agent that ever sees the user's original description.questions.md. They never see the task. This structurally prevents opinion-bias in research findings./team Add rate limiting middleware to all API endpoints
For well-understood bugs, skip the QRSPI ceremony:
/team-fix Users see stale cache after profile update
Or run individual phases:
/team-question Add rate limiting middleware to all API endpoints
/team-research docs/plans/<id>/
/team-design docs/plans/<id>/
/team-structure docs/plans/<id>/
/team-plan docs/plans/<id>/
/team-worktree docs/plans/<id>/
/team-implement docs/plans/<id>/
/team-pr docs/plans/<id>/
Each command after /team-question takes the artifact directory printed by
the previous step (docs/plans/<id>/) as its single argument.
claude plugin add /path/to/team
See docs/architecture.md for the full architecture, the artifact frontmatter schema, and the phase-inference rules.
agents/ — decoupled workers that read predecessor artifacts from docs/plans/ and write their outputs thereskills/ — slash commands, the standalone /shipit land utility, and shared methodologieshooks/ — safety guards and docs/plans/-aware compaction resilienceskills/team/registry.json — phase-tagged inventory of the 13 agentsdocs/plans/<id>/*.md — <id> is <TICKET>-<topic> or <YYYY-MM-DD>-<topic>. Each artifact carries YAML frontmatter (topic, date, phase; gated artifacts also carry approved, approved_at, revision). Live in-session coordination uses TodoWrite.npx claudepluginhub bostonaholic/team --plugin teamSkills for using the Reflect CLI
No description provided.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Multi-agent orchestration for Claude Code. 12 specialized agents working in parallel — planning, building, reviewing, debugging. Plus a Hub for always-alive multi-project sessions controllable from Telegram or Slack.
Long-running agent harness with 5-layer memory architecture, GitHub integration, autonomous batch processing, Agent Teams with ATDD, 9 hooks (safety, quality gates, team coordination), and 6 Agent Skills
AI team workflow harness for Claude Code — specialist agents, shared skills, slash commands, hooks, and staged delegation pipeline.
Multi-agent team orchestration for parallel task execution, research, and implementation
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.