nullhack/temple8
Test-driven agent orchestration, templated. Tests authored as the contract, simulated before any source exists, built red→green under flowr state machines. Any LLM, any process, zero lock-in.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/nullhack/temple8 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 nullhack/temple8/.opencode/skills/author-test-stubs .claude/skills/author-test-stubs $ npx degit nullhack/temple8/.opencode/skills/confirm-red-failure .claude/skills/confirm-red-failure $ npx degit nullhack/temple8/.opencode/skills/consolidate-interview .claude/skills/consolidate-interview $ npx degit nullhack/temple8/.opencode/skills/derive-source-stubs .claude/skills/derive-source-stubs $ npx degit nullhack/temple8/.opencode/skills/design-interaction .claude/skills/design-interaction $ npx degit nullhack/temple8/.opencode/skills/design-visual-asset .claude/skills/design-visual-asset $ npx degit nullhack/temple8/.opencode/skills/implement-from-stub .claude/skills/implement-from-stub $ npx degit nullhack/temple8/.opencode/skills/instantiate-project .claude/skills/instantiate-project $ npx degit nullhack/temple8/.opencode/skills/interview-building-blocks .claude/skills/interview-building-blocks $ npx degit nullhack/temple8/.opencode/skills/interview-cross-cutting .claude/skills/interview-cross-cutting $ npx degit nullhack/temple8/.opencode/skills/interview-general .claude/skills/interview-general $ npx degit nullhack/temple8/.opencode/skills/merge-to-dev .claude/skills/merge-to-dev $ npx degit nullhack/temple8/.opencode/skills/model-data-schema .claude/skills/model-data-schema $ npx degit nullhack/temple8/.opencode/skills/publish-release .claude/skills/publish-release $ npx degit nullhack/temple8/.opencode/skills/record-cassette .claude/skills/record-cassette $ npx degit nullhack/temple8/.opencode/skills/record-decision .claude/skills/record-decision $ npx degit nullhack/temple8/.opencode/skills/refactor-green .claude/skills/refactor-green $ npx degit nullhack/temple8/.opencode/skills/refresh-cycle .claude/skills/refresh-cycle $ npx degit nullhack/temple8/.opencode/skills/research-provider .claude/skills/research-provider $ npx degit nullhack/temple8/.opencode/skills/review-implementation .claude/skills/review-implementation $ npx degit nullhack/temple8/.opencode/skills/review-test-stubs .claude/skills/review-test-stubs $ npx degit nullhack/temple8/.opencode/skills/select-build-target .claude/skills/select-build-target $ npx degit nullhack/temple8/.opencode/skills/select-external-target .claude/skills/select-external-target $ npx degit nullhack/temple8/.opencode/skills/ship-unit .claude/skills/ship-unit $ npx degit nullhack/temple8/.opencode/skills/simulate-contracts .claude/skills/simulate-contracts $ npx degit nullhack/temple8/.opencode/skills/write-probe .claude/skills/write-probe $ npx degit nullhack/temple8/.opencode/skills/write-test-py .claude/skills/write-test-py
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (27)
author-test-stubsconfirm-red-failureconsolidate-interviewderive-source-stubsdesign-interactiondesign-visual-assetimplement-from-stubinstantiate-projectinterview-building-blocksinterview-cross-cuttinginterview-generalmerge-to-devmodel-data-schemapublish-releaserecord-cassetterecord-decisionrefactor-greenrefresh-cycleresearch-providerreview-implementationreview-test-stubsselect-build-targetselect-external-targetship-unitsimulate-contractswrite-probewrite-test-py
Similar rigs
molefrog/moi
💾 MOI: agent-agnostic generative UI workspace. Give your agent a skill and let it build software around itself.
Pragmatist 3.5k tok · · Q18
threadnote/threadnote
Local-first engineering memory and large-scale polyglot graph search for Codex, Claude, Cursor, Copilot, and the next agent you try.
Pragmatist 3.2k tok · · Q8
moi-computer/moi
💾 Moi: agent-agnostic generative UI workspace. Give your agent a skill and let it build software around itself.
Pragmatist 7.3k tok · · Q18
chillax97/edu4self
A local learning dashboard where Claude Code is your tutor. Lessons, grading, and a room you like.
Pragmatist 1.9k tok · · Q0