agent-teams

Plugin agent-teams from marketplace ilia-izmailov-plugins in izmailovilya/ilia-izmailov-plugins. Commands read from the repo's manifest — 1 month ago.

Skills (3)

• conventions

  Analyze codebase and create/update .conventions/ directory with gold standards, anti-patterns, and checks. Use this skill when the user asks to 'set up conventions', 'create coding standards', 'extract patterns from the codebase', 'document how code should be written', 'create gold standards', 'esta

• interviewed-team-feature

  Conducts a short adaptive interview (2-6 questions) to understand intent, then launches /team-feature with a compiled brief. Use this skill when the user asks to 'interview before building', 'discuss feature before implementation', 'ask me questions first', 'let's talk about what to build', 'I have

• team-feature

  Launch Agent Team for feature implementation with review gates (coders + a per-task reviewer + final verification). Use this skill whenever the user asks to 'build a feature', 'implement this', 'code this', 'add functionality', 'create a component/page/API', 'launch agent team', 'team feature', or g

Subagents (11)

• architect

  Specialized architect for COMPLEX feature teams, Phase 1 only. Critiques the plan from their expertise and debates with other architects in Lead-run rounds until consensus, then writes a domain review brief for the reviewer and stands down. Never reviews code. Three personas: Frontend (UI/UX/compone

• browser-verifier

  One-shot browser verifier that uses Chrome extension to verify UI: page loads, elements visible, interactions work, no console errors. Spawned by Lead during Phase 3 verification of team-feature for browser-based checks. <example> Context: Verify skill spawns browser-verifier with UI checks lead: "V

• ci-verifier

  One-shot CI verifier that runs build, typecheck, lint, and test commands. Reports PASS/FAIL/BROKEN per command with evidence. Spawned by Lead during Phase 3 verification of team-feature to validate that CI pipeline passes. <example> Context: Build fails but tests pass assistant: "BUILD: FAIL — 3 Typ

• codebase-researcher

  One-shot explorer that scans a project and returns a condensed summary of stack, structure, patterns, and conventions. Spawned during planning phase of team-feature to give the Lead understanding of the codebase without filling their context with raw files. <example> Context: Lead needs to understan

• coder

  Temporary implementation agent for feature teams. Receives a task with gold standard examples, implements matching patterns, runs self-checks, requests review directly from the team reviewer, fixes feedback, and commits. Spawned per task, shut down after completion. <example> Context: Coder requests

• proxy-teammate

  Thin team member that carries a role (reviewer, tech-lead, architect, coder) inside the Claude team while delegating the actual thinking to an external CLI agent (Codex, Kimi, Grok, Cursor). Keeps one external session alive per role so follow-up rounds remember earlier ones, triages the external out

• reference-researcher

  One-shot explorer that finds canonical reference files (gold standards) and returns their FULL content. These files become few-shot examples in coder prompts. Spawned during planning phase of team-feature. <example> Context: Lead needs reference implementations for coders to follow lead: "Find canon

• risk-tester

  One-shot risk investigator that verifies specific risks BEFORE implementation begins. Spawned per risk during Step 4b of team-feature pipeline. Unlike reviewers (who read finished code), risk testers investigate whether a risk is real by reading existing code AND writing/running test scripts when em

• spec-verifier

  One-shot spec verifier that checks acceptance criteria: file existence, exports, API responses, config values. Spawned by Lead during Phase 3 verification of team-feature to validate that implementation meets the spec. <example> Context: Verify skill spawns spec-verifier with acceptance criteria lea

• tech-lead

  Permanent architectural authority for MEDIUM feature teams. Validates plans, identifies risks, rules on escalations and review loops, maintains DECISIONS.md, and runs the final cross-task consistency check. Does not review individual tasks — unified-reviewer does. Works inside agent-teams for the en

• unified-reviewer

  The one per-task code reviewer on every feature team, at every complexity level. Covers security, logic, quality and fit with the plan in a single priority-ordered pass, and goes deep where the task touches auth, payments, migrations or shared infrastructure. <example> Context: Task touches auth mid

Similar plugins