Agent building

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

Retrospective of one Claude Code session, built from its jsonl log and published as a single artifact page — where the time went (AI working vs.

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims…

Assess a codebase's readiness for AI agent contributors using the layered contract model, and generate a complexity hotspot SVG treemap (size = LOC, hue =…

Harden a skill or any agent instruction file (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules, .github/copilot-instructions.md) through judge-panel refinement…

Install Claude Code hooks that block selected destructive Git operations when the user requests guardrails.

Run MUSE /resume, /save and /bye for continuous work in Codex or Claude Code, preserving the selected role, Lane, decisions and source evidence across sessions.

Build, edit, or review Superwall paywall, onboarding, and web2app flows from a local coding agent with terminal access.

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure.

Repo-local Sage eval-gauge / hill-climbing Phase-0 toolkit.

Repo-local focused Sage capability, adapter, and notification validation workflow.

Repo-local Sage trace, Phoenix, Mythic task-output, and run-log analysis workflow.

Master context engineering for AI agent systems.

Use when the user asks to invoke, delegate to, or collaborate with Codex on any task.

Defensive Bash scripting for production automation, CI scripts, and agent-facing tools.

Claude Code internals - hooks, skill frontmatter, headless mode, and extension debugging, current as of June 2026.

Build and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcome scoring, adversarial refuters, and…

Router and composition workflows for Figma via the official Figma MCP: which Figma skill/tool for which job, capture-to-canvas (screenshots or shotcraft crops…

Landing discipline for parallel work: sequential test-gated landing queue, pre-land scrub, auto-rebase of in-flight lanes, fleet status, one-shot revert…

Git + worktree orchestrator: status survey, per-worktree triage, commits, PRs, branches, releases, rebases — reads inline, writes to a background agent.

Analyze Claude Code session logs and surface productivity improvements.

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama…

Prevent and investigate Rust reliability failures in agent-written or human-written code through enforceable API and lint restrictions, ownership and…

CLI and agent skill for personal LoRAs, image, video, and music generation using Sogni AI's decentralized GPU network.