71 tagged kanban, measured the same way as everything else here.
Browse within: coding-agents 45git-worktree 45vibe-coding 45task-management 8Multi-Agent 7ai-dlc 7
Agent
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the Idea. Spawn via the blocking subagent tool after the last task of an idea-rooted proposal is verified.
Agent
Review submitted Chorus proposals for quality — check document completeness, task granularity, AC alignment, and cross-task dependencies. Spawn via the blocking subagent tool after choruspmsubmitproposal.
Agent
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the Idea. Spawn after the last task of an idea-rooted proposal is verified.
Agent Claude Code
Review PRs against this checklist. Be concise - only comment on actual issues.
Agent
Daily automated standup with WhatsApp delivery to two groups (Executive + Motivational).
Agent
Document strategic initiatives in automagik-roadmap with guided template selection.
Agent
Autonomous wish coordinator with Genie orchestrator validation.
Agent
Configure Claude Code as your AI coding agent.
Agent
Configure OpenAI Codex as your AI coding agent.
Agent
AI coding agents compatible with Operator.
Agent
Use this agent to generate or update semantic summaries in .metis/code-index.md. Trigger after structural indexing (metis index) to add AI-generated understanding of what the code means — not just what symbols exist. Runs as a background subagent to avoid consuming main context. IMPORTANT: Requires permission setup.…
Agent
Use this agent when working with Metis documents and needing methodology guidance. Helps with document type selection, work decomposition, phase transitions, and Flight Levels best practices. Context: User wants to track some work but isn't sure what document type to use user: "I need to track this bug fix, what…
Agent
How the engineering skills read this repo's domain documentation before they explore the code.
Agent
Tickets for this repo live as markdown files in .scratch/, and the board bakes them to the Pages demo on every push. The tickets are public copy.
Agent
The skills speak in five canonical triage roles. This file maps those roles to the strings this repo uses. A ticket carries its role in the status field of its frontmatter.
Agent
Cheap executor for mechanical, spec-complete chores with an unambiguous "done" — kanban card moves, git mv/rename/delete, formatting, inventory/listing, grep "where is X", and fully-specified edits (rename a symbol, bump a config value across files, apply a lint-fix). Hand off deterministic single-pass work that needs…
Agent
Read-only database schema introspection for any project. Returns concise schema summaries (table → columns → PK → indexes → FKs) from the live DB, migrations, or config. Hand off when the main thread is about to grep through migration files or run multiple SHOW CREATE TABLE round-trips. Never writes, never runs…
Agent
Read-only incident triage and "why did X fail" investigations on any project. Pulls container logs (Portainer), application logs (Graylog), and metrics (Grafana/Prometheus), then returns a focused timeline + likely root cause — not a raw log dump. Use proactively when the user reports an error, 500, slow request…
Samuel0101010/wisp-orchestrator
Agent
Invoke to implement exactly one task from tasks.md. Reads architecture.md as a binding constraint, writes code, and stops after one logical commit.
Samuel0101010/wisp-orchestrator
Agent
Invoke to convert a Goal plus a Team specification into a valid Plan DAG written to plan.json. Used once per harness run before agents are dispatched.
Samuel0101010/wisp-orchestrator
Agent
Invoke after a developer commit to run build, test, and lint and emit a BMAD-style PASS/CONCERNS/FAIL gate verdict as JSON. Read-only; never modifies code.
Agent Claude Code
Architectural coherence observer for Cos. Called ONCE by the dev loop after it has written a plan and before it implements. Reads the plan against CLAUDE.md and the decision log, and returns a coherence observation. In Phase 1 it is a silent listener — it records and reports, it never approves, blocks, or sends a plan…
Rijul1204/rashedul-agentic-engineering
Agent
Runs the repo's quality gates (lint, format, typecheck, dead-code, scoped tests) and returns a concise pass/fail report. Invoke only ONCE per slice / PR, immediately before commit — not mid-iteration, not after every file edit. Before delegating, the caller should run the project's auto-formatter on touched files…