{
  "markdown": "<p align=\"center\">\n  <img src=\"plugins/shelldon/assets/shelldon.svg\" width=\"120\" />\n</p>\n\n<h1 align=\"center\">Shelldon</h1>\n\n<p align=\"center\">\n  <strong>Semantic Heuristic Execution & Logic Layer (S.H.E.L.L.)</strong>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://github.com/DyxBenjamin/shelldon/stargazers\"><img src=\"https://img.shields.io/github/stars/DyxBenjamin/shelldon?style=flat&color=yellow\" alt=\"Stars\"></a>\n  <a href=\"https://github.com/DyxBenjamin/shelldon/commits/main\"><img src=\"https://img.shields.io/github/last-commit/DyxBenjamin/shelldon?style=flat\" alt=\"Last Commit\"></a>\n  <a href=\"LICENSE\"><img src=\"https://img.shields.io/github/license/DyxBenjamin/shelldon?style=flat\" alt=\"License\"></a>\n</p>\n\n---\n\n**Shelldon** is a specialized cognitive protocol for AI engineering agents. It implements the **S.H.E.L.L.** (Semantic Heuristic Execution & Logic Layer) standard to minimize token overhead while maximizing technical signal.\n\nBy eliminating conversational prose and adopting axiomatic logic, Shelldon reduces **output token volume by ~75%** and **input context by ~46%**, resulting in faster inference, reduced costs, and lower cognitive load for developers.\n\n## The Shelldon Logic\n\nShelldon treats the LLM response as a high-density telemetry stream rather than a natural language dialogue.\n\n| Metric | Normal Agent | Shelldon (S.H.E.L.L.) |\n| :--- | :--- | :--- |\n| **Output Density** | High (Conversational) | Ultra-High (Axiomatic) |\n| **Token Savings** | 0% | ~75% |\n| **Inference Speed** | Baseline | ~3x Improvement |\n| **Technical Signal** | Diffuse | Concentrated |\n\n### Comparative Analysis\n\n#### 🗣️ Conventional Response (69 tokens)\n> \"The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object.\"\n\n#### 🪨 Shelldon Response (19 tokens)\n> \"New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`.\"\n\n---\n\n## Operational Modes\n\nShelldon supports multiple intensity levels to match your workflow requirements:\n\n| Mode | Standard | Application |\n| :--- | :--- | :--- |\n| **Verbose** | STE (Simplified Technical English) | Technical documentation, complex explanations. |\n| **Strict** | Default Fragmented Protocol | Standard development and debugging. |\n| **Axiomatic** | Pure Logic Mapping (`->`, `=>`) | High-speed, repetitive engineering tasks. |\n| **SOAP** | Diagnostic Grid (Subjective/Objective/Assessment/Plan) | Systematic bug analysis and RCA. |\n\n---\n\n## Capabilities & Sub-Skills\n\n### 🛠️ shell-commit\nGenerates high-density, telemetry-compliant Conventional Commits. Eliminates narrative noise while preserving architectural intent.\n- `feat(api): add GET /users/:id/profile [INFO] Client payload optimization.`\n\n### 🔍 shell-review\nExecutes deterministic, one-line evaluations per finding. Focuses exclusively on topological integrity and type safety.\n- `L42 [ERR] user(null) -> panic => inject guard.`\n\n### 🗜️ shell-compress\nMinifies context files (e.g., `CLAUDE.md`, `GEMINI.md`) into axiomatic logic. Reduces session-start token consumption by **~46%**.\n\n---\n\n## Installation\n\nShelldon is agent-agnostic and supports major AI engineering environments:\n\n### Gemini CLI\n```bash\ngemini extensions install https://github.com/DyxBenjamin/shelldon\n```\n\n### Claude Code\n```bash\nclaude plugin marketplace add DyxBenjamin/shelldon\nclaude plugin install shell@shell\n```\n\n### Multi-Agent Support (Cursor, Windsurf, Cline, Copilot)\n```bash\nnpx skills add DyxBenjamin/shelldon\n```\n\n---\n\n## Empirical Validation\n\nBenchmarked against standard models using the `benchmarks/` evaluation harness.\n\n| Task | Normal (tokens) | Shelldon (tokens) | Efficiency |\n| :--- | :---: | :---: | :---: |\n| React Re-render Diagnosis | 1180 | 159 | **87%** |\n| Auth Middleware Fix | 704 | 121 | **83%** |\n| Database Connection Pooling | 2347 | 380 | **84%** |\n| **Composite Average** | **1214** | **294** | **65%** |\n\n### Theoretical Foundation\nBased on research indicating that brevity constraints in large language models can enhance technical accuracy by reducing hallucinatory drift. (See: [\"Brevity Constraints Reverse Performance Hierarchies\"](https://arxiv.org/abs/2604.00025)).\n\n---\n\n## License\n\nMIT © [DyxBenjamin](https://github.com/DyxBenjamin)\n",
  "bytes": 4453,
  "sha": "7ad77132c01dda3f5291e0e00a1af27acd8cbbbb1687333b474e9842b7ae4057",
  "repo_slug": "dyxbenjamin/shelldon",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_dyxbenjamin_shelldon_770b8ff5/readme"
}