parallel-adversarial-r…
Two skills for adversarial code review, plus an eval suite.
2 skills18
@prime-radiant-incDevelopment
Plugin
greenfield
Reverse engineer clean behavioral specs from any codebase. Greenfield reads source code, documentation, SDKs, runtime behavior, and binaries, then produces behavioral specifications, test vectors, acceptance criteria, and a full provenance trail.
Plugin Signal69/100Solid
maintained58
capable69
documented100
adopted53
Claude Code
$ npx -y skills add prime-radiant-inc/greenfield --agent claude-code
Codex
$ npx skills add prime-radiant-inc/greenfield -a codex
Cursor
$ npx skills add prime-radiant-inc/greenfield -a cursor
Gemini CLI
$ npx skills add prime-radiant-inc/greenfield -a gemini-cli
GitHub Copilot
$ npx skills add prime-radiant-inc/greenfield -a github-copilot
OpenCode
$ npx skills add prime-radiant-inc/greenfield -a opencode
Windsurf
$ npx skills add prime-radiant-inc/greenfield -a windsurf
Stats
303
Stars
30
Forks
Maintained
Maintenance
Apache-2.0
License
Last commit
Created
In this plugin
- skills
- analysis-pipeline
- autonomous-discovery
- behavioral-spec-writing
- binary-analysis
- community-intelligence
- container-execution
- contract-detection
- doc-research
- ecosystem-analysis
- fidelity-validation
- git-archaeology
- incremental-analysis
- multi-source-synthesis
- provenance-methodology
- runtime-observation
- second-pass-review
- source-analysis
- source-completeness
- spec-sanitization
- test-suite-analysis
- validation-methodology
- visual-exploration
- agents
- commands
What's inside
22 Skills
- /autonomous-discovery
- /behavioral-spec-writing
- /binary-analysis
- /community-intelligence
- /container-execution
- /contract-detection
- /doc-research
- /ecosystem-analysis
- /fidelity-validation
- /git-archaeology
- /incremental-analysis
- /multi-source-synthesis
- /provenance-methodology
- /runtime-observation
- /second-pass-review
- /source-analysis
- /source-completeness
- /spec-sanitization
- /test-suite-analysis
- /validation-methodology
- /visual-exploration
2 Agents
analyzerGeneric Analyzer agent. Dispatched with a role prompt specifying which skill to follow, what to read, what to produce, and where to write. Loads all analysis skills.sanitizerGeneric sanitizer worker agent. Reads raw specs and rewrites them as clean behavioral specs. Loads sanitization and provenance skills.
README
Greenfield
Reverse engineer clean behavioral specs from any codebase.
Greenfield 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.
Greenfield is a Claude Code plugin. It runs inside the claude CLI and uses Claude agents as the workers that read code, write specs, and audit output.
Installation
/plugin marketplace add prime-radiant-inc/prime-radiant-marketplace
/plugin install greenfield@prime-radiant-marketplace
Restart Claude Code after installing.
Usage
Extract specs
claude
> /analyze /path/to/target
/analyze 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.
Target 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.
Workspace output:
workspace/
├── raw/ # Analysis artifacts with source references
├── output/ # Sanitized specs for the implementation team
│ ├── specs/
│ ├── test-vectors/
│ └── validation/
└── provenance/ # Citation audit trail
Re-sanitize an existing workspace
claude
> /sanitize /path/to/workspace
Re-runs the sanitization pass on an existing workspace. Useful when the initial pass left contamination that the audit caught.
Implement from the output specs
Greenfield stops at the specs. The implementation team reads workspace/output/ and builds against the behavioral specs, test vectors, and acceptance criteria there.
How it works
The 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:
- 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. - sanitizer — rewrites raw specs into output specs free of implementation details. Dispatched during Layer 5 and for remediation during Layers 6 and 7.
Pipeline
| Layer | Roles | Output |
|---|---|---|
| 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 |
| L2: Synthesis | feature-discoverer, architecture-analyst, api-extractor, synthesizer, module-mapper | Feature inventory, architecture model, module map |
| L3: Deep Docs | deep-dive-analyzer, behavior-documenter, user-journey-analyzer, contract-extractor | Behavioral specs, journeys, contracts |
| Gate 1 | spec-verifier | Correctness, contradictions, gaps |
| Gate 1b | source-completeness-checker | Every user-facing surface captured |
| L4: Validation | test-vector-generator, test-generator, acceptance-criteria-writer | Test vectors, test specs, acceptance criteria |
| Gate 2 | spec-reviewer | Implementation leakage, completeness, quality |
| L5: Sanitization | sanitizer | Output specs rewritten from understanding, not copied |
| L6: Review | structural, content, completeness reviewers + deep-read auditors | Second-pass contamination review |
| L7: Fidelity | fidelity-validators | Flags behavioral detail lost or weakened during sanitization |
License
Apache 2.0. Copyright 2026 Prime Radiant, Inc.
Stars on GitHub
Momentum
- stars in total
- 303
File tree
More plugins by @prime-radiant-inc.
View @prime-radiant-inc’s profile@prime-radiant-inciterative-development
A Claude Code plugin that runs an iterative, audited implementation loop for projects with large or ambiguous specs. It extracts requirements, plans iterations, implements tasks test-first, and audits progress.
6 skills183
@prime-radiant-incsprout
A self-improving, multi-agent AI system that decomposes tasks and delegates to specialist agents. Sprout is an autonomous coding assistant built on a recursive agent architecture, where every action is a goal-directed delegation to a subagent.
36 agents113
@prime-radiant-incSimilar plugins.
superpowers
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
15 skills1 hook311k
@obraskills
Helps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
31 skills309k
@mattpocockecc
Gives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
200 skills71 agents1 MCP+3+2+2+2+2+2+2+1+1293k
@affaan-mreact
Developer tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
14 skills4 agents252k
@facebookQuestions about greenfield.
Install it with the command on its page. It includes analysis-pipeline, autonomous-discovery, behavioral-spec-writing. Its skills do not fire on their own yet. Free and open source.
- What is greenfield?
- prime-radiant-inc/greenfield is a plugin that reverse engineers behavioral specs from existing codebases, drawing on source code, docs, SDKs, runtime behavior and binaries. Use it when you need test vectors, acceptance criteria and a full provenance trail for software you did not write.
- How do I install greenfield?
- Run these in Claude Code: npx -y skills add prime-radiant-inc/greenfield --agent claude-code. Then prompt normally.
- Does greenfield auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is greenfield free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use greenfield's skills?
- greenfield installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it