{
  "markdown": "# STiFLeR's Claude Code Plugins\n\n[![GitHub stars](https://img.shields.io/github/stars/STiFLeR7/claude-plugins?style=flat)](https://github.com/STiFLeR7/claude-plugins/stargazers)\n[![memex-mcp on npm](https://img.shields.io/npm/dm/stifler-memex-mcp?label=memex-mcp%20installs)](https://www.npmjs.com/package/stifler-memex-mcp)\n[![memex-mcp on PyPI](https://img.shields.io/pypi/dm/memex-mcp?label=memex-mcp%20pypi)](https://pypistats.org/packages/memex-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n\nA small, opinionated marketplace of Claude Code plugins focused on durable engineering context and grounded agent workflows.\n\n```\n/plugin marketplace add STiFLeR7/claude-plugins\n/plugin install memex-mcp@stifler-marketplace\n/plugin install prompt-forge@stifler-marketplace\n```\n\n## Plugins\n\n### 🧠 [memex-mcp](./memex-mcp)\n\nTrusted engineering context for AI coding agents. Builds a temporal knowledge graph of your repository and exposes bounded, provenance-aware context through 14 MCP tools — `get_project_context`, `record_decision`, `predict_impact`, `explain_change`, and more.\n\nClaude Code can explicitly recover your architecture, decisions, open problems, and code relationships without treating the plugin as a replacement for Git or Claude's own session memory.\n\n- Bitemporal facts with expiry and supersession\n- Confidence decay, validation, corroboration, and stale-context review\n- Bounded `ContextPacket` projections with provenance and selection reasons\n- Human-in-the-loop validation via `memex review`\n- Explicit, governed writes for decisions, problems, resolutions, and invalidation\n\nBacked by Neo4j + Graphiti; optional LLM backends support synthesis and explanation. MIT licensed. → [github.com/STiFLeR7/memex](https://github.com/STiFLeR7/memex)\n\n### ✍️ [prompt-forge](./prompt-forge)\n\nAdvanced prompt refinement skill. Extracts your *real* intent, investigates your codebase and ecosystem, applies 9 perspective lenses (Security, QA, UX, Performance, …), and produces a grounded prompt for your execution tool — without ever executing the task itself.\n\nTrigger phrases: *\"help me prompt\"*, *\"improve my prompt\"*, *\"how to write a prompt for…\"*. The skill investigates, asks sharp clarifying questions, then hands you a refined prompt to paste into your next agent.\n\nMIT licensed. → [github.com/STiFLeR7/prompt-forge](https://github.com/STiFLeR7/prompt-forge)\n\n## Local development\n\n```bash\n# Clone and link as a local marketplace for testing\ngit clone https://github.com/STiFLeR7/claude-plugins\n/plugin marketplace add /absolute/path/to/claude-plugins\n```\n\n## Contributing\n\nPlugins added to this marketplace should be:\n- Single-purpose and well-tested\n- Documented with clear trigger conditions\n- MIT (or compatible) licensed\n- Maintained by an active author\n\nOpen an issue with a proposal before submitting a PR.\n\n## License\n\nMIT — see individual plugin directories for their respective licenses.\n",
  "bytes": 2955,
  "sha": "8161b12f5faa9f49a39dcb2682339b2399ba9fe1d3776e0d6dcda0e695bac50e",
  "repo_slug": "stifler7/claude-plugins",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_stifler7_claude_plugins_memex_mcp_287ad3ac/readme"
}