socialadsmentor/sam-agentic-harness
A working Claude Code harness scrubbed from a production agency setup: always-on rules, on-demand skills, hooks, model-scored subagents, three-tier memory, and a self-improvement loop gated by human approval. The installer checks fit and wa
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 socialadsmentor/sam-agentic-harness/.claude ./rig-sam-agentic-harness # inspect, then merge into .claude/ 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 socialadsmentor/sam-agentic-harness/.claude/skills/harness-install .claude/skills/harness-install $ npx degit socialadsmentor/sam-agentic-harness/skills/ab-test-setup .claude/skills/ab-test-setup $ npx degit socialadsmentor/sam-agentic-harness/skills/accessibility-compliance .claude/skills/accessibility-compliance $ npx degit socialadsmentor/sam-agentic-harness/skills/accessibility .claude/skills/accessibility $ npx degit socialadsmentor/sam-agentic-harness/skills/agent-architecture-audit .claude/skills/agent-architecture-audit $ npx degit socialadsmentor/sam-agentic-harness/skills/agent-eval .claude/skills/agent-eval $ npx degit socialadsmentor/sam-agentic-harness/skills/agent-harness-construction .claude/skills/agent-harness-construction $ npx degit socialadsmentor/sam-agentic-harness/skills/agent-introspection-debugging .claude/skills/agent-introspection-debugging $ npx degit socialadsmentor/sam-agentic-harness/skills/agentic-engineering .claude/skills/agentic-engineering $ npx degit socialadsmentor/sam-agentic-harness/skills/ai-regression-testing .claude/skills/ai-regression-testing $ npx degit socialadsmentor/sam-agentic-harness/skills/ai-seo .claude/skills/ai-seo $ npx degit socialadsmentor/sam-agentic-harness/skills/anthropic-courses .claude/skills/anthropic-courses $ npx degit socialadsmentor/sam-agentic-harness/skills/anthropic-sdk-php .claude/skills/anthropic-sdk-php $ npx degit socialadsmentor/sam-agentic-harness/skills/anthropic-sdk-python .claude/skills/anthropic-sdk-python $ npx degit socialadsmentor/sam-agentic-harness/skills/api-connector-builder .claude/skills/api-connector-builder $ npx degit socialadsmentor/sam-agentic-harness/skills/architecture-decision-records .claude/skills/architecture-decision-records $ npx degit socialadsmentor/sam-agentic-harness/skills/architecture-patterns .claude/skills/architecture-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/article-writing .claude/skills/article-writing $ npx degit socialadsmentor/sam-agentic-harness/skills/async-python-patterns .claude/skills/async-python-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/auth-implementation-patterns .claude/skills/auth-implementation-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/backend-patterns .claude/skills/backend-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/bash-defensive-patterns .claude/skills/bash-defensive-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/bats-testing-patterns .claude/skills/bats-testing-patterns $ npx degit socialadsmentor/sam-agentic-harness/skills/block-no-verify-hook .claude/skills/block-no-verify-hook $ npx degit socialadsmentor/sam-agentic-harness/skills/blueprint .claude/skills/blueprint $ npx degit socialadsmentor/sam-agentic-harness/skills/brainstorming .claude/skills/brainstorming $ npx degit socialadsmentor/sam-agentic-harness/skills/browser-testing-with-devtools .claude/skills/browser-testing-with-devtools $ npx degit socialadsmentor/sam-agentic-harness/skills/churn-prevention .claude/skills/churn-prevention $ npx degit socialadsmentor/sam-agentic-harness/skills/ci-cd-and-automation .claude/skills/ci-cd-and-automation $ npx degit socialadsmentor/sam-agentic-harness/skills/citation-engine .claude/skills/citation-engine $ npx degit socialadsmentor/sam-agentic-harness/skills/ck .claude/skills/ck $ npx degit socialadsmentor/sam-agentic-harness/skills/claude-code-security-review .claude/skills/claude-code-security-review $ npx degit socialadsmentor/sam-agentic-harness/skills/claude-cookbooks .claude/skills/claude-cookbooks $ npx degit socialadsmentor/sam-agentic-harness/skills/click-path-audit .claude/skills/click-path-audit $ npx degit socialadsmentor/sam-agentic-harness/skills/codebase-onboarding .claude/skills/codebase-onboarding $ npx degit socialadsmentor/sam-agentic-harness/skills/coding-standards .claude/skills/coding-standards $ npx degit socialadsmentor/sam-agentic-harness/skills/competitor-alternatives .claude/skills/competitor-alternatives $ npx degit socialadsmentor/sam-agentic-harness/skills/connections-optimizer .claude/skills/connections-optimizer $ npx degit socialadsmentor/sam-agentic-harness/skills/content-engine .claude/skills/content-engine $ npx degit socialadsmentor/sam-agentic-harness/skills/content-hash-cache-pattern .claude/skills/content-hash-cache-pattern
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 (103)
harness-installab-test-setupaccessibility-complianceaccessibilityagent-architecture-auditagent-evalagent-harness-constructionagent-introspection-debuggingagentic-engineeringai-regression-testingai-seoanthropic-coursesanthropic-sdk-phpanthropic-sdk-pythonapi-connector-builderarchitecture-decision-recordsarchitecture-patternsarticle-writingasync-python-patternsauth-implementation-patternsbackend-patternsbash-defensive-patternsbats-testing-patternsblock-no-verify-hookblueprintbrainstormingbrowser-testing-with-devtoolschurn-preventionci-cd-and-automationcitation-engineckclaude-code-security-reviewclaude-cookbooksclick-path-auditcodebase-onboardingcoding-standardscompetitor-alternativesconnections-optimizercontent-enginecontent-hash-cache-patterncontext-budgetcontext-driven-developmentcontext-engineeringcontinuous-agent-loopcost-aware-llm-pipelinecost-aware-routingcost-trackingcouncilcqrs-implementationcrosspostcustomer-billing-opsdashboard-builderdata-scraper-agentdata-storytellingdata-throughput-acceleratordeployment-patternsdocker-patternsdocumentation-and-adrse2e-testingerror-handlingeval-harnessfrontend-a11yfrontend-patternsgit-workflow-and-versioninggithub-actions-templateshexagonal-architectureincident-runbook-templatesincremental-implementationjavascript-testing-patternsmicroservices-patternsmodern-javascript-patternsnextjs-app-router-patternsnodejs-backend-patternsperformance-optimizationplanning-and-task-breakdownpostgres-patternspostmortem-writingprisma-patternspython-design-patternsreact-patternsreact-performancereact-state-managementreact-testingreceiving-code-reviewredis-patternsrequesting-code-reviewresponsive-designsecrets-managementsecurity-and-hardeningsecurity-reviewsession-selftestshellcheck-configurationspec-driven-developmentsql-optimization-patternssystematic-debuggingtdd-workflowtypescript-advanced-typesusing-git-worktreesverification-before-completionvite-patternswcag-audit-patternsworkflow-orchestration-patternswriting-plans
Similar rigs
chefcurry30the-boop/claude-dotfiles
Portable Claude Code + Cursor config: skills, agents, settings — sync across machines
Skill Collector 8.0k tok ·
idiaz01/enterprise-superpowers
CLI tool that scaffolds Claude Code plugins for enterprise teams with skills, agents, commands, rules, hooks, and MCP server configs.
Skill Collector 4.4k tok ·
mturac/everything-openai-codex
EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.
MCP Hoarder 47.1k tok ·
goharabbas321/zeoel-framework
A production-grade multi-agent orchestration framework for building enterprise-grade products. Powered by **22 highly specialized AI agents**, isolated Git Worktrees, strict Red-Green-Refactor TDD, and rigorous multi-stage verification.
Orchestrator 10.2k tok ·