Structured software development workflows for Claude Code, aligned with Opus 4.8 at xhigh/max effort. Eleven reusable subagents drive brief generation, plan generation, task decomposition, automated batch implementation, and multi-angle parallel review. v3 follows five design rules: workflow SOP stays, business rules…
Switch Claude Code between Anthropic direct and custom LLM gateway profiles via slash commands. Bring-your-own-URL, bring-your-own-key, zero secret material stored in plugin files.
Universal loop-engineering harness: machine-verifiable stop conditions, cross-model maker/checker (Codex maker, Claude checker), disk-based loop memory, reversibility×impact decision gates that keep human approval to irreversible actions while auto-pushing reversible work-branch commits, autonomous replan on stalls, a.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Verbatim recall across Claude Code sessions, plus a gate that stops oversized skills from flooding the prompt. Pure Node, no dependencies, no API calls.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Fase Zero do Agent-Driven Protocol (ADP): as 2 primeiras fases do metodo spec-driven para Claude Code. grill-me (a IA te entrevista ate o escopo ficar redondo) + to-prd (a conversa vira um PRD de verdade) + CLAUDE.coringa.md (convencoes para adaptar ao seu projeto). Gratis. O protocolo completo (6 fases, 4 gates…
★not rated 1 2mo agoA
tokens not measured
originalMIT
Structured decision-making for Claude Code: a /method command, an auto-triggering methodology-driven-thinking skill, and a red-team-critic subagent. 29 analytical frameworks (Cynefin, First Principles, OODA, ACH, Pre-mortem, Red Team, BATNA, JTBD, Theory of Constraints, ...) applied explicitly — not nominally.
★not rated 1 3mo 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 3mo agoA
tokens not measured
originalMIT
The godspeed methodology — a routing-and-orchestration pipeline for Claude Code. Fires on the word 'godspeed': scores the prompt on S0-S5 complexity, routes to the cheapest model that handles it well, dispatches parallel Sonnet workers for S3+ tasks, critic-gates the synthesis, and persists PASSing answers to a vector.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Custom statusline for Claude Code: context usage with color alerts and emotes, token counts with thousands separator, session/weekly rate limit usage and subagent rows with token speed.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Persistent memory for Claude Code. Auto-archives every session to your Obsidian vault, injects recent work at startup, and adds /recall to search your whole history.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Praxis: the disciplined practice of engineering, applied automatically in Claude Code. A per-prompt router turns any request, typed or commanded, into a full pipeline: restructure into a spec, investigate, plan, implement to production standard with professional code-craft and the right best-practices, then run an…
★not rated 1 1mo agoA
tokens not measured
originalMIT
Claude Code skills and agents for Home Assistant development — custom integrations (Python), Lovelace cards (TypeScript/JavaScript), blueprints / automations (YAML), and ESPHome / add-on work.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Zero-dependency sound notifications for Claude Code. Plays audible alerts via PermissionRequest and Stop hooks — know when Claude needs approval or has finished, without watching the terminal. macOS / Linux / Windows.
★not rated 1 3mo agoA
tokens not measured
originalMIT