codemirket/harness
Reusable agent skills, project workflows and executable verification tools for Codex Desktop and Claude Desktop Code.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http openai-docs https://developers.openai.com/mcp $ claude mcp add --transport http microsoft-learn https://learn.microsoft.com/api/mcp $ npx degit codemirket/harness/skills ./rig-harness/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.
$ claude mcp add --transport http openai-docs https://developers.openai.com/mcp $ claude mcp add --transport http microsoft-learn https://learn.microsoft.com/api/mcp
$ npx degit codemirket/harness/skills/advanced-motion .claude/skills/advanced-motion $ npx degit codemirket/harness/skills/agent-coordination .claude/skills/agent-coordination $ npx degit codemirket/harness/skills/ai-system-evaluation .claude/skills/ai-system-evaluation $ npx degit codemirket/harness/skills/architecture-review .claude/skills/architecture-review $ npx degit codemirket/harness/skills/backend-engineering .claude/skills/backend-engineering $ npx degit codemirket/harness/skills/brand-guidelines .claude/skills/brand-guidelines $ npx degit codemirket/harness/skills/ci-maintenance .claude/skills/ci-maintenance $ npx degit codemirket/harness/skills/context-management .claude/skills/context-management $ npx degit codemirket/harness/skills/conversion-review .claude/skills/conversion-review $ npx degit codemirket/harness/skills/customer-research .claude/skills/customer-research $ npx degit codemirket/harness/skills/data-analysis .claude/skills/data-analysis $ npx degit codemirket/harness/skills/data-migrations .claude/skills/data-migrations $ npx degit codemirket/harness/skills/database-systems .claude/skills/database-systems $ npx degit codemirket/harness/skills/debugging .claude/skills/debugging $ npx degit codemirket/harness/skills/desktop-integration .claude/skills/desktop-integration $ npx degit codemirket/harness/skills/document-parsing .claude/skills/document-parsing $ npx degit codemirket/harness/skills/document-workflow .claude/skills/document-workflow $ npx degit codemirket/harness/skills/engineering-judgment .claude/skills/engineering-judgment $ npx degit codemirket/harness/skills/executive-strategy .claude/skills/executive-strategy $ npx degit codemirket/harness/skills/experiment-design .claude/skills/experiment-design $ npx degit codemirket/harness/skills/frontend-engineering .claude/skills/frontend-engineering $ npx degit codemirket/harness/skills/infrastructure-engineering .claude/skills/infrastructure-engineering $ npx degit codemirket/harness/skills/interface-design .claude/skills/interface-design $ npx degit codemirket/harness/skills/marketing-writing .claude/skills/marketing-writing $ npx degit codemirket/harness/skills/mcp-integration .claude/skills/mcp-integration $ npx degit codemirket/harness/skills/mobile-design .claude/skills/mobile-design $ npx degit codemirket/harness/skills/motion-design .claude/skills/motion-design $ npx degit codemirket/harness/skills/office-authoring .claude/skills/office-authoring $ npx degit codemirket/harness/skills/page-transitions .claude/skills/page-transitions $ npx degit codemirket/harness/skills/performance-engineering .claude/skills/performance-engineering $ npx degit codemirket/harness/skills/product-management .claude/skills/product-management $ npx degit codemirket/harness/skills/project-scaffolding .claude/skills/project-scaffolding $ npx degit codemirket/harness/skills/release-operations .claude/skills/release-operations $ npx degit codemirket/harness/skills/research-and-synthesis .claude/skills/research-and-synthesis $ npx degit codemirket/harness/skills/search-audit .claude/skills/search-audit $ npx degit codemirket/harness/skills/search-visibility .claude/skills/search-visibility $ npx degit codemirket/harness/skills/security-judgment .claude/skills/security-judgment $ npx degit codemirket/harness/skills/skill-catalog .claude/skills/skill-catalog $ npx degit codemirket/harness/skills/svg-animation .claude/skills/svg-animation $ npx degit codemirket/harness/skills/svg-creation .claude/skills/svg-creation
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 *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| OpenAI Developer Docs · "openai-docs" | remote · remote | 1.0k |
| Microsoft Learn Docs · "microsoft-learn" | remote · remote | 1.2k |
Skills (43)
advanced-motionagent-coordinationai-system-evaluationarchitecture-reviewbackend-engineeringbrand-guidelinesci-maintenancecontext-managementconversion-reviewcustomer-researchdata-analysisdata-migrationsdatabase-systemsdebuggingdesktop-integrationdocument-parsingdocument-workflowengineering-judgmentexecutive-strategyexperiment-designfrontend-engineeringinfrastructure-engineeringinterface-designmarketing-writingmcp-integrationmobile-designmotion-designoffice-authoringpage-transitionsperformance-engineeringproduct-managementproject-scaffoldingrelease-operationsresearch-and-synthesissearch-auditsearch-visibilitysecurity-judgmentskill-catalogsvg-animationsvg-creationsystems-engineeringtest-designwork-planning
Similar rigs
thixpin/claude-config
A reusable Claude Code configuration for agentic coding and software engineering workflows. It provides global engineering guidelines, debugging and bug-fixing workflows, code review, security auditing, testing skills, and reusable develope
Pragmatist 1.5k tok ·
martingarramon/claude-code-starter-kit
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + persistent Memory. Rules from mistakes, not pre-optimization.
Skill Collector 1.5k tok ·
HAR5HA-7663/My_Claude_Setup
Full export of my Claude Code setup — settings, skills, agents, hooks, statusline, plugins, MCP configs + agent install instructions
Skill Collector 7.5k tok ·
aiskillstore/marketplace
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Skill Collector 2.6k tok ·