[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75453":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":14,"starSnapshotCount":14,"syncStatus":13,"lastSyncTime":28,"discoverSource":29},75453,"greenfield","prime-radiant-inc\u002Fgreenfield","prime-radiant-inc","A Claude Code plugin that reverse-engineers clean behavioral specs, test vectors, and acceptance criteria from any codebase, producing a provenance trail so a fresh team can reimplement without inheriting the original's internal structure.",null,154,13,4,2,0,7,9,39,21,65.84,"Apache License 2.0",false,"main",true,[],"2026-06-12 04:01:18","# Greenfield\n\n**Reverse engineer clean behavioral specs from any codebase.**\n\nGreenfield reads source code, documentation, SDKs, runtime behavior, and binaries, then produces behavioral specifications, test vectors, acceptance criteria, and a full provenance trail. The output describes *what* the software does — not *how* any particular codebase does it — so a fresh implementation team can build against the specs without inheriting the original's internal structure.\n\nGreenfield is a [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code) plugin. It runs inside the `claude` CLI and uses Claude agents as the workers that read code, write specs, and audit output.\n\n## Installation\n\n```bash\n\u002Fplugin marketplace add prime-radiant-inc\u002Fprime-radiant-marketplace\n\u002Fplugin install greenfield@prime-radiant-marketplace\n```\n\nRestart Claude Code after installing.\n\n## Usage\n\n### Extract specs\n\n```bash\nclaude\n> \u002Fanalyze \u002Fpath\u002Fto\u002Ftarget\n```\n\n`\u002Fanalyze` runs a seven-layer pipeline. It discovers the available intelligence sources (source, docs, SDK, community, runtime, binary, git history, tests, UI, contracts), gathers evidence from each, synthesizes behavioral specs with provenance citations, generates test vectors and acceptance criteria, sanitizes the specs of implementation details, then runs a second-pass review of the result.\n\nTarget shape doesn't matter. Greenfield has been used on single-file minified JavaScript bundles and on source-tree projects; the pipeline also has a path for decompiled native binaries. The methodology adapts to what's there.\n\nWorkspace output:\n\n```\nworkspace\u002F\n├── raw\u002F         # Analysis artifacts with source references\n├── output\u002F      # Sanitized specs for the implementation team\n│   ├── specs\u002F\n│   ├── test-vectors\u002F\n│   └── validation\u002F\n└── provenance\u002F  # Citation audit trail\n```\n\n### Re-sanitize an existing workspace\n\n```bash\nclaude\n> \u002Fsanitize \u002Fpath\u002Fto\u002Fworkspace\n```\n\nRe-runs the sanitization pass on an existing workspace. Useful when the initial pass left contamination that the audit caught.\n\n### Implement from the output specs\n\nGreenfield stops at the specs. The implementation team reads `workspace\u002Foutput\u002F` and builds against the behavioral specs, test vectors, and acceptance criteria there.\n\n## How it works\n\nThe pipeline dispatches agents with role-specific prompts across the seven layers. Each dispatch runs one of two generic agent types loaded with a specific skill:\n\n- **analyzer** — the workhorse. Reads evidence and writes specs. Dispatched under many roles across layers: `discovery-agent`, `bundle-splitter`, `chunk-analyzer`, `function-analyzer`, `doc-researcher`, `community-analyst`, `sdk-analyzer`, `cli-explorer`, `behavior-observer`, `feature-discoverer`, `architecture-analyst`, `api-extractor`, `synthesizer`, `module-mapper`, `deep-dive-analyzer`, `behavior-documenter`, `user-journey-analyzer`, `contract-extractor`, `spec-verifier`, `source-completeness-checker`, `test-vector-generator`, `test-generator`, `acceptance-criteria-writer`, `spec-reviewer`, `structural-leakage-reviewer`, `content-contamination-reviewer`, `behavioral-completeness-reviewer`, `deep-read-auditor`, `fidelity-validator`.\n- **sanitizer** — rewrites raw specs into output specs free of implementation details. Dispatched during Layer 5 and for remediation during Layers 6 and 7.\n\n### Pipeline\n\n| Layer | Roles | Output |\n|-------|-------|--------|\n| L1: Intelligence | bundle-splitter, chunk-analyzer, function-analyzer, doc-researcher, community-analyst, sdk-analyzer, cli-explorer, behavior-observer | Raw evidence from source, docs, SDK, community, runtime, binary |\n| L2: Synthesis | feature-discoverer, architecture-analyst, api-extractor, synthesizer, module-mapper | Feature inventory, architecture model, module map |\n| L3: Deep Docs | deep-dive-analyzer, behavior-documenter, user-journey-analyzer, contract-extractor | Behavioral specs, journeys, contracts |\n| Gate 1 | spec-verifier | Correctness, contradictions, gaps |\n| Gate 1b | source-completeness-checker | Every user-facing surface captured |\n| L4: Validation | test-vector-generator, test-generator, acceptance-criteria-writer | Test vectors, test specs, acceptance criteria |\n| Gate 2 | spec-reviewer | Implementation leakage, completeness, quality |\n| L5: Sanitization | sanitizer | Output specs rewritten from understanding, not copied |\n| L6: Review | structural, content, completeness reviewers + deep-read auditors | Second-pass contamination review |\n| L7: Fidelity | fidelity-validators | Flags behavioral detail lost or weakened during sanitization |\n\n## License\n\nApache 2.0. Copyright 2026 Prime Radiant, Inc.\n","Greenfield 是一个可以从任何代码库反向工程生成清晰行为规范的工具。其核心功能包括读取源代码、文档、SDKs、运行时行为和二进制文件，并生成行为规范、测试向量、验收标准以及完整的溯源轨迹。这些输出描述了软件的功能，而非特定实现细节，使得新的开发团队能够基于这些规范进行开发而无需继承原有代码结构。该项目特别适合于需要对现有系统进行重构或迁移但希望保持原有功能不变的场景。作为Claude Code的一个插件，Greenfield通过Claude CLI运行，并利用Claude代理执行分析任务。","2026-06-11 03:52:49","CREATED_QUERY"]