Plugin Claude Code
A team of AI specialists for Claude Code: 7 agents with distinct roles, 14 skills, and a dev workflow with machine-verifiable completion. This is how ToruAI works with Claude Code internally.
Plugin Claude Code
A dev pipeline for Claude Code that will not call work done until tests, lint and a security audit all exit zero. Seven specialists run it, for 1.1k tokens of always-on context.
MCP server Claude CodeCodexCursor +2
Git-native memory for AI agents — markdown knowledge in .megg/ folders that travels with your repo. MCP server + CLI for Claude Code. Runs locally from the megg npm package.
Agent
Finds the pattern in messy data and says which parts the numbers actually support. Use for analysis, metrics, validating an assumption before you build on it.
Agent
Technical Builder - builds elegant systems, ensures feasibility, executes with quality. Use when code needs writing, systems need building, or technical problems need solving.
Agent
Chief of Staff & Strategic Director. Use for strategic decisions, delegating to other agents, coordinating work across projects, vision alignment, and improving AI workflows. Use proactively when planning work, making decisions, or optimizing how we work.
Agent
Designs interfaces and flows that remove decisions instead of adding controls. Use for UI, UX flows, design systems, and accessibility.
Agent
Writes and pressure-tests client-facing communication — pitches, proposals, hard emails. Use when the audience is outside your team.
Agent
Codebase Explorer & Research Synthesizer. Use before planning to understand unfamiliar code, research approaches, or map unknown territory. Fast, thorough, read-only.
Agent
Security specialist for code audits, vulnerability scanning, dependency checks, and security best practices. Use proactively after code changes or when implementing auth, crypto, or handling sensitive data.
Skill Claude CodeCodex
Branch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.
Skill Claude CodeCodex
Look up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.
Skill Claude CodeCodex
Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.
Skill Claude CodeCodex
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
Skill Claude CodeCodex
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
Skill Claude CodeCodex
Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.
Skill Claude CodeCodex
Run the project's own tests, linter, type checker and build, and report what actually failed.
Skill Claude CodeCodex
The last gate before merge — QA, security audit, review and changelog, with objective pass conditions.
Skill Claude CodeCodex
Audit the code for vulnerabilities, leaked secrets and risky dependencies before it ships.
Skill Claude CodeCodex
Save a project fact, decision or gotcha so your next session already knows it.
Skill Claude CodeCodex
Hand off an unfinished session to the next one — what's done, what's next, what's blocked.
Skill Claude CodeCodex
Write the spec before the code, then check the built thing against it — so agents build what was agreed, not what they invented.
Skill Claude CodeCodex
Map unfamiliar code or research an approach before planning, read-only and fast.
Skill Claude CodeCodex
Turn friction you just hit into a concrete change to the workflow, so the same problem doesn't recur.