secret-keeper

What a Claude Code session has in context: budget, files and how much of each was read, stale files, skills, helper agents, and what compaction summarised.

hooks

A skill that designs and critiques dashboards by Stephen Few's Information Dashboard Design: what belongs on a single glanceable screen, bullet graphs and sparklines over gauges and pies, layout, color and highlighting, the thirteen common mistakes, and Few's own palette and drawing specs taken from the book's figures.

1 skill

One MCP server for any REST API or remote MCP server: Claude names an alias from your config and the gateway calls it with that alias's API key, token or headers, switching mid-session with no reload. Keys stay in the config, never in the transcript.

1 MCP server

A skill for Supabase projects in development: flattens supabase/migrations/ into a supabase/schemas/ tree exported by pg-delta, applies edits to it straight to the dev database with no migration files, resets the database to the latest schema plus seed, and writes one baseline migration when the project goes live.

1 skill

Drives your Claude Code sessions on its own: asks you pointed questions first when a prompt leaves the goal, constraints or check unclear, rewrites a session's first prompt, decides permission asks from the whole conversation and Claude's questions once you've gone quiet, and after each turn sends the practical next step (fix, verify, commit on a branch) until only you can decide what is left, the push and the PR included.

Requip for Claude Code: named loadouts of skills, MCP servers and instructions, one equipped per project from the /loadout picker or by Claude itself, the rest switched off. Switching never needs a restart.

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents