Structured decision-making for Claude Code: a /method command, an auto-triggering methodology-driven-thinking skill with an evidence-gated product-research mode, a red-team-critic subagent, an evidence-scout subagent, and a hook that checks their JSON reports (needs Node.js). 33 analytical frameworks (Cynefin, First…
★not rated 1
changed 10d agoA
tokens not measured
originalMIT
Give your AI agent an operating contract. Twelve build principles — the CEO/CTO division of labor, grill-me-before-you-build, reality-graded honesty — actively enforced through composable skills and a session-start hook. Stop your agent from being a yes-man.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Self-learning project context — bare /prime-context captures the session's learnings into area context files; /prime-context loads context on demand; thin AGENTS.md router, structure audit (doctor), drift warnings at session start.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Copies queries, shell commands and config snippets from Claude's responses to the clipboard on macOS, Linux and Windows — proactively, or on demand via /clipboard:copy.
★not rated 1 3mo agoA
tokens not measured
originalMIT
A collection of Claude Code skills for general software-engineering work — each a self-contained, named methodology you invoke by intent. terry (agent-fleet orchestration AND a producer-consumer task queue with backpressure — a long-running manager loop that drives parallel worker agents across isolated git worktrees.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Faz o Claude Code rodar com modelos OpenAI (gpt-5.5, gpt-5-codex, etc.) usando sua assinatura ChatGPT Pro/Plus — sem OPENAIAPIKEY. Empacota o proxy raine/claude-code-proxy com instalação por escopo (global/projeto/sessão).
Detects and fixes drift between a project's Claude artifacts (CLAUDE.md, skills, commands, agents, hooks/settings, and native/MCP memory) and the project's actual current reality: broken references, stale context, and legacy-narration framing that should read forward-looking.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Recreate a website or web app as a Remotion promo video — pixel-faithful to the site's own design tokens, choreographed clicks/scrolls/zooms, rendered to MP4. Code, not screen recording.
★not rated 1 4mo agoA
tokens not measured
originalMIT
📝 Subagents inherit none of your durable rules — not your CLAUDE.md, memory or plugin nudges. brief-agents scans all three into one compact /.claude/agent-briefing-index.md, regenerated when the sources change. A SessionStart hook nudges you to brief subagents, and a PreToolUse hook blocks unbriefed Agent/Task code d.
★not rated 1
changed 2d agoA
tokens not measured
originalMIT
A Stop-hook guard that won't let an AI agent quit until its goals are provably complete. Re-injects the unfinished checklist on every attempt to stop, and double-checks the work in strict mode.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Cognitive infrastructure for the SRF Online Teachings Portal. 43 skills (37 analytical + 6 SRF mission), 9 commands, 2 practices, and 8 agents (4 domain-agnostic + 4 SRF-specialized) for team members and autonomous agents.
★not rated 1 7mo agoA
tokens not measured
originalMIT
Multi-server SSH management for Claude Code. Inventory of servers with an active-server model, guided setup, SSH key deployment, connectivity diagnostics, and system status across a fleet of Linux hosts.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Convert any feature idea, plan, PRD, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, and refactors. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt, a progress tracker, and a reviews…
★not rated 1 4mo agoA
tokens not measured
originalMIT
Llama Steve analyzes your actual product to identify and ship game-changing features. Maximize your conversion, cut user friction, and focus only on what wins.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Deploy to Vercel, Railway, Fly.io, and Render directly from Claude Code. Auto-detects your framework, runs preflight checks, and handles preview and production deployments with rollback safety.