prime-radiant-inc/greenfield
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.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit prime-radiant-inc/greenfield/skills ./rig-greenfield/skills MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit prime-radiant-inc/greenfield/skills/analysis-pipeline .claude/skills/analysis-pipeline $ npx degit prime-radiant-inc/greenfield/skills/autonomous-discovery .claude/skills/autonomous-discovery $ npx degit prime-radiant-inc/greenfield/skills/behavioral-spec-writing .claude/skills/behavioral-spec-writing $ npx degit prime-radiant-inc/greenfield/skills/binary-analysis .claude/skills/binary-analysis $ npx degit prime-radiant-inc/greenfield/skills/community-intelligence .claude/skills/community-intelligence $ npx degit prime-radiant-inc/greenfield/skills/container-execution .claude/skills/container-execution $ npx degit prime-radiant-inc/greenfield/skills/contract-detection .claude/skills/contract-detection $ npx degit prime-radiant-inc/greenfield/skills/doc-research .claude/skills/doc-research $ npx degit prime-radiant-inc/greenfield/skills/ecosystem-analysis .claude/skills/ecosystem-analysis $ npx degit prime-radiant-inc/greenfield/skills/fidelity-validation .claude/skills/fidelity-validation $ npx degit prime-radiant-inc/greenfield/skills/git-archaeology .claude/skills/git-archaeology $ npx degit prime-radiant-inc/greenfield/skills/incremental-analysis .claude/skills/incremental-analysis $ npx degit prime-radiant-inc/greenfield/skills/multi-source-synthesis .claude/skills/multi-source-synthesis $ npx degit prime-radiant-inc/greenfield/skills/provenance-methodology .claude/skills/provenance-methodology $ npx degit prime-radiant-inc/greenfield/skills/runtime-observation .claude/skills/runtime-observation $ npx degit prime-radiant-inc/greenfield/skills/second-pass-review .claude/skills/second-pass-review $ npx degit prime-radiant-inc/greenfield/skills/source-analysis .claude/skills/source-analysis $ npx degit prime-radiant-inc/greenfield/skills/source-completeness .claude/skills/source-completeness $ npx degit prime-radiant-inc/greenfield/skills/spec-sanitization .claude/skills/spec-sanitization $ npx degit prime-radiant-inc/greenfield/skills/test-suite-analysis .claude/skills/test-suite-analysis $ npx degit prime-radiant-inc/greenfield/skills/validation-methodology .claude/skills/validation-methodology $ npx degit prime-radiant-inc/greenfield/skills/visual-exploration .claude/skills/visual-exploration
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (22)
analysis-pipelineautonomous-discoverybehavioral-spec-writingbinary-analysiscommunity-intelligencecontainer-executioncontract-detectiondoc-researchecosystem-analysisfidelity-validationgit-archaeologyincremental-analysismulti-source-synthesisprovenance-methodologyruntime-observationsecond-pass-reviewsource-analysissource-completenessspec-sanitizationtest-suite-analysisvalidation-methodologyvisual-exploration
Similar rigs
Kairos-ai-agent/kairos-code
Self-hosted multi-agent coding pipeline with an enforced review gate and a cost ledger — you don't ship what the agent didn't pass. (AGPL-3.0)
Skill Collector 5.1k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·