tomcounsell

tomcounsell/ai

Agent Claude Code

Subagent dispatched by do-test to classify test failures as regressions vs pre-existing by running failing tests against main. Returns structured JSON classification.

tomcounsell/ai

Agent Claude Code

Implementation agent that executes ONE task at a time. Use when work needs to be done - writing code, creating files, implementing features.

tomcounsell/ai

Agent Claude Code

Expert code reviewer focusing on correctness, maintainability, security, and adherence to project standards.

tomcounsell/ai

Agent Claude Code

Scans PR diffs for legacy patterns that should have been cleaned up.

tomcounsell/ai

Agent Claude Code

Developer subagent for eng sessions — owns the SDLC pipeline (plan, critique, build, test, review, patch, docs, merge) for work the PM routes. Spawned by the PM session on first need and CONTINUED across turns and process restarts via agent continuation; never spawn a second dev for the same session.

tomcounsell/ai

Agent Claude Code

Documentation specialist with deep knowledge of the full documentation structure, ensuring nothing gets missed.

tomcounsell/ai

Agent Claude Code

Frontend web testing specialist that uses BYOB MCP to execute UI test scenarios and return structured results. Receives a focused test task (URL + what to verify) and returns pass/fail with evidence.

tomcounsell/ai

Agent Claude Code

Handles project management, issue tracking, sprint planning, and team coordination via Linear. Invoke for queries about issues, tickets, sprints, cycles, roadmaps, backlogs, or team velocity.

tomcounsell/ai

Agent Claude Code

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai

Agent Claude Code

Creates structured feature plans. Repo-specific configuration for plan creation subagents.

tomcounsell/ai

Agent Claude Code

Plan critic — reviews, challenges, and validates implementation plans.

tomcounsell/ai

Agent Claude Code

Handles cloud infrastructure, deployments, and service management via Render. Invoke for queries about deploying services, checking logs, scaling instances, managing environment variables, or infrastructure operations.

tomcounsell/ai

Agent Claude Code

Handles error monitoring, performance analysis, and application observability via Sentry. Invoke for queries about errors, bugs, crashes, exceptions, alerts, stack traces, performance issues, or application health.

tomcounsell/ai

Agent Claude Code

Runs a comprehensive multi-dimensional strategic analysis on any business question. Spawns parallel analytical passes, cross-examines results, synthesizes a structured assessment, and writes an HTML report. Returns only the report file path.

tomcounsell/ai

Agent Claude Code

Handles payment processing, subscriptions, billing, and revenue analytics via Stripe API. Invoke for queries about payments, refunds, customers, MRR, ARR, invoices, or any financial operations related to Stripe.

tomcounsell/ai

Agent Claude Code

Focuses on implementing comprehensive testing strategies with real integrations and AI judges.

tomcounsell/ai

Agent Claude Code

Read-only validation agent that verifies work meets acceptance criteria. Use after a builder finishes to verify quality.

tomcounsell/ai

Command Claude Code

These rails apply to every session-runner session (PM, Dev, and Teammate roles). Each role prime instructs you to read and apply this file before acting.

tomcounsell/ai

Command Claude Code

Prime the Dev (developer) persona for the headless session runner. No task is present in $ARGUMENTS — the runner will relay the PM's first instruction separately.

tomcounsell/ai

Command Claude Code

Prime the PM (project manager) persona for the headless session runner. Receives the user message as $ARGUMENTS.

tomcounsell/ai

Command Claude Code

Prime the Teammate persona for the headless session runner. Receives the user message as $ARGUMENTS.

tomcounsell/ai

Command Claude Code

Bring this machine to latest main — sync deps, verify environment, restart services. Runs deterministically via inline bash execution, not model discretion.

tomcounsell/ai

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing user_prompt_submit.py. From tomcounsell/ai.

tomcounsell/ai

Hook Claude Code

Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing pre_tool_use.py, pre_tool_use_bash.py and validate_design_system_readonly.py (3 commands). From tomcounsell/ai.