Productivity & Automation for Claude Code

Analyzes codebase and writes structured intel files to .planning/intel/.

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd:new-project orchestrator.

Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.

The Cynic of the life team. Sarcastic friend with a sharp eye. Roasts the user's excuses, teases the melodrama, and cuts through the performance with a laugh that lands.

The Pusher of the life team. Young, ambitious, restless. Pushes the user out of their comfort zone, toward the bold move, the unknown country, the thing they will regret not trying.

Background agent that extracts user profiles, contact cards, and behavioral patterns from chat history. Runs as a daemon service every 30 min.

Agent that analyzes projects to create WORK (unit of work) and decompose sub-TASKs. Must be used for requests like "plan this", "decompose TASKs", "build XXX", "add XXX feature". Reads CLAUDE.md, README, and source code to create WORK and derive sub-TASKs.

Mechanical scp-and-spawn for autonomous Claude Code agents on a remote host. Use when a task exceeds Claude Code's interactive timeout, when work needs to run on a different machine than the human, or when delegating to a long-running agent. Captures the actual claude binary PID (not the bash wrapper PID — load-bearing detail), saves to a PID file, and returns DISPATCHED or BLOCKED with structured evidence. Does not interpret the spec, modify it, or make strategic decisions — purely a launch pri

Agent that manages the TASK dependency DAG for a specific WORK and executes the pipeline. Must be used for requests like "run WORK-XX", "execute pipeline", "next task". Reads the WORK's PLAN.md and dispatches builder → verifier → committer sequentially according to dependency order.

Agent that analyzes user requests to create requirement specifications and WORK units. Must be used when "[]" tags are detected. For simple requirements, assumes Planner role to create PLAN.md + TASKs directly.

Operations execution agent. Finds what's falling through the cracks — stale work, broken processes, missing automation, communication failures. What the CEO doesn't see.

Generates and executes REST and GraphQL API test suites covering happy paths, auth scenarios, edge cases, and contract validation, then reports results with coverage metrics. Use when automating endpoint regression testing or building a new test suite. Trigger with "test this API", "generate API tests".

Analyzes audio tracks and prescribes a complete mixing workflow — EQ, compression, noise reduction, sidechain ducking, and platform-specific loudness targets — for broadcast-quality results. Use when mixing tutorial or vlog audio. Trigger with \"mix my audio\", \"fix my voice track\".

Plans efficient batch recording sessions that group multiple videos by topic, manage energy and breaks, and produce detailed run-of-show schedules to maximize output per recording day. Use when scheduling a recording block. Trigger with \"plan batch recording session\", \"schedule my recording day\".

Use this agent when mapping bead dependencies — finding bottlenecks (open issues blocking the most other open work), detecting dependency cycles, or reasoning about the critical path through a bd Dolt database.

Use this agent for general beads (bd) expertise — the three-layer mirror (bd to GitHub to Plane via bd-sync), plain-English bead naming, the JSONL throttle and export model, the source-of-truth hierarchy, and bead hygiene audits. It is the generalist that explains bd discipline and points to the specialist agents for sync, epic-closure, dependency, and recovery work.

Design ticket workflows, SLA tiers, knowledge-base structures, and escalation paths for stage-appropriate support operations. Use when building or auditing a support operation from triage to Tier 3. Trigger with "design a support workflow", "build a support knowledge base".

Use when a task has been triaged and the chain needs to decide which specialist agents are responsible — the router consulted once after triage to finalize the reviewer/investigator roster, web-research scope, and fan-out approvals.

Analyzes git commit history to produce structured build logs, flag hero moments worth filming, and generate video script outlines from real development work. Use when turning a coding session into content. Trigger with \"log my build\", \"extract content from my commits\".

Designs and maintains CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI) including builds, tests, quality gates, secrets management, and deployment strategies, then reports conformity with sprint specs. Use when setting up or fixing CI/CD for a project. Trigger with "set up CI/CD", "fix pipeline".

Use this agent when the user requests coding assistance with a declared assistance level (1-4) or mentions graduated assistance, pair programming, or preventing skill atrophy.

Identifies compatible creator partners, drafts outreach pitches, and produces detailed collaboration project plans with timelines, responsibilities, and cross-promotion strategies. Use when planning a collab or guest appearance. Trigger with \"find collaboration partners\", \"plan a creator collab\".

Orchestrates the full geepers_* agent fleet — routing requests to the correct topic orchestrator or individual specialist, logging dispatch decisions, and synthesizing cross-agent results. Use when starting a dev session, unsure which geepers agent to use, or running a checkpoint suite. Trigger with "start my session", "coordinate the geepers agents".

Fetches raw analytics data from Umami MCP across all tracked sites and returns structured datasets for specialist agents — never interprets, only collects. Use when kicking off an analytics pipeline or pulling fresh metrics for any time range. Trigger with \"collect analytics data\", \"fetch site metrics\".

Generates realistic, locale-aware test data (users, products, orders, custom schemas) using Faker.js, Factory Boy, or json-schema-faker — producing factory functions, database seed scripts, and fixture files ready for immediate use. Use when setting up a test environment or populating a dev database with production-scale data. Trigger with \"generate test data\", \"create seed data factories\".

Run a full freshie ecosystem discovery scan via rebuild-inventory.py and report plugin, skill, and pack delta against the previous run stored in the SQLite inventory database. Use when refreshing the inventory after adding plugins or tracking ecosystem growth over time. Trigger with \"run discovery scan\", \"scan the inventory\".

Plans and generates multi-platform content distribution strategies with platform-specific metadata, timing, and cross-promotion linking. Use when publishing a video across YouTube, TikTok, LinkedIn, and more. Trigger with \"distribute my content\", \"plan multi-platform release\".

Detects copy-pasted code blocks (10+ lines), near-clones, and repeated patterns that warrant abstraction — using jscpd and grep-based analysis, with a hard bias against premature extraction. Use when you suspect significant code duplication is inflating maintenance burden. Trigger with \"find duplicate code\", \"DRY audit\".

Designs CDN configurations, cache strategies, and edge function deployments to minimize latency globally. Use when you need to optimize cache hit ratios, design edge routing, or deploy Cloudflare Workers/Lambda@Edge. Trigger with \"design CDN config\", \"optimize cache strategy\".

Brief description of agent's specialty (20-200 chars)

Automate FairDB PostgreSQL-as-a-Service operations — proactive monitoring, incident response, customer onboarding, backup verification, query optimization, and capacity planning with a human-escalation decision framework. Use when handling routine maintenance, investigating performance incidents, or provisioning a new database customer. Trigger with \"fairdb operations\", \"run health check\".

Sole authority for Caddy configuration changes — adds routes, manages port allocation, validates before reload, and creates backups. Use when deploying a new service, fixing routing errors, or resolving port conflicts. Trigger with "add a Caddy route", "fix 502 on this path".

Synchronizes admin dashboards, registers new services for persistence via service_manager.py, and verifies all dashboards reflect accurate system state after reboots. Use when adding a new service or verifying the system after a restart. Trigger with "sync the dashboard", "register this service for persistence".

Analyzes query plans, recommends indexes, and diagnoses N+1 patterns, lock contention, and missing pagination for SQLite and PostgreSQL databases. Use when a search endpoint is slow or the database shows signs of needing to scale. Trigger with "analyze slow queries", "optimize the database".

Generates README files, setup guides, API docs, and dependency guides from existing code. Use when a project needs end-user documentation or a fresh dev needs setup instructions. Trigger with \"document this project\", \"write the README\".

Applies game-design principles to non-game apps — XP systems, streaks, leaderboards, achievement badges, and feedback loops. Use when a product needs higher engagement or motivation mechanics. Trigger with \"add gamification\", \"make this more engaging\".

Cost-optimized code generator using tiered model routing — cheap models for boilerplate, mid-tier for logic, high-tier only for security-critical paths. Use when generating bulk code on a budget. Trigger with \"generate code cheaply\", \"draft the implementation\".