first-fluke/oh-my-agent
Mechanical verification for AI coding agents — skills pack or full harness (stop-hook gates, artifact checks, independent judges).
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http context7 https://mcp.context7.com/mcp $ claude mcp add serena -e SERENA_LOG_LEVEL=YOUR_SERENA_LOG_LEVEL -- oma bridge --context oma $ claude mcp add aside -- aside mcp $ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest --no-usage-statistics --isolated $ claude mcp add good-stdio -e FIXTURE=YOUR_FIXTURE -- echo hello $ claude mcp add --transport http good-http https://example.com/mcp $ claude mcp add --transport http insecure-http http://example.com/mcp $ claude mcp add shell-string -- 'npx -y something' $ npx degit first-fluke/oh-my-agent/skills ./rig-oh-my-agent/skills $ npx degit first-fluke/oh-my-agent/hooks ./rig-oh-my-agent/hooks
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 context7 https://mcp.context7.com/mcp $ claude mcp add serena -e SERENA_LOG_LEVEL=YOUR_SERENA_LOG_LEVEL -- oma bridge --context oma $ claude mcp add aside -- aside mcp $ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest --no-usage-statistics --isolated $ claude mcp add good-stdio -e FIXTURE=YOUR_FIXTURE -- echo hello $ claude mcp add --transport http good-http https://example.com/mcp $ claude mcp add --transport http insecure-http http://example.com/mcp $ claude mcp add shell-string -- 'npx -y something'
$ npx degit first-fluke/oh-my-agent/.agents/skills/oma-academic-writing .claude/skills/oma-academic-writing $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-architecture .claude/skills/oma-architecture $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-backend .claude/skills/oma-backend $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-brainstorm .claude/skills/oma-brainstorm $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-coordination .claude/skills/oma-coordination $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-db .claude/skills/oma-db $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-debug .claude/skills/oma-debug $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-deepsec .claude/skills/oma-deepsec $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-design .claude/skills/oma-design $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-dev-workflow .claude/skills/oma-dev-workflow $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-docs .claude/skills/oma-docs $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-explanation .claude/skills/oma-explanation $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-frontend .claude/skills/oma-frontend $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-hwp .claude/skills/oma-hwp $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-image .claude/skills/oma-image $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-market .claude/skills/oma-market $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-mobile .claude/skills/oma-mobile $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-observability .claude/skills/oma-observability $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-orchestration .claude/skills/oma-orchestration $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-pdf .claude/skills/oma-pdf $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-pm .claude/skills/oma-pm $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-qa .claude/skills/oma-qa $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-recap .claude/skills/oma-recap $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-refactor .claude/skills/oma-refactor $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-scholar .claude/skills/oma-scholar $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-scm .claude/skills/oma-scm $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-search .claude/skills/oma-search $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-skill-creation .claude/skills/oma-skill-creation $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-slide .claude/skills/oma-slide $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-tf-infra .claude/skills/oma-tf-infra $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-translation .claude/skills/oma-translation $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-video .claude/skills/oma-video $ npx degit first-fluke/oh-my-agent/.agents/skills/oma-voice .claude/skills/oma-voice $ npx degit first-fluke/oh-my-agent/.cursor-plugin/skills/oma-bootstrap .claude/skills/oma-bootstrap $ npx degit first-fluke/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-orchestrator .claude/skills/oma-orchestrator $ npx degit first-fluke/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-skill-creator .claude/skills/oma-skill-creator $ npx degit first-fluke/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-translator .claude/skills/oma-translator $ npx degit first-fluke/oh-my-agent/cli/platform/emit/__fixtures__/repo/.agents/skills/folded-desc-skill .claude/skills/folded-desc-skill $ npx degit first-fluke/oh-my-agent/cli/platform/emit/__fixtures__/repo/.agents/skills/invalid-skill .claude/skills/invalid-skill $ npx degit first-fluke/oh-my-agent/cli/platform/emit/__fixtures__/repo/.agents/skills/oversized-skill .claude/skills/oversized-skill
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 (10)
| server | source | est. tokens |
|---|---|---|
| Context7 | remote · remote | 1.2k |
| oma · "serena" env: SERENA_LOG_LEVEL | binary | 2.5k |
| aside | binary | 2.5k |
| Chrome DevTools MCP · "chrome-devtools" | npm | 9.0k |
| echo · "good-stdio" env: FIXTURE | binary | 2.5k |
| example.com · "good-http" | remote · remote | 2.5k |
| loopback-http | local / custom · remote | 2.5k |
| example.com · "insecure-http" | remote · remote | 2.5k |
| something · "shell-string" | npm | 2.5k |
| bad-entry | local / custom | 2.5k |
Skills (41)
oma-academic-writingoma-architectureoma-backendoma-brainstormoma-coordinationoma-dboma-debugoma-deepsecoma-designoma-dev-workflowoma-docsoma-explanationoma-frontendoma-hwpoma-imageoma-marketoma-mobileoma-observabilityoma-orchestrationoma-pdfoma-pmoma-qaoma-recapoma-refactoroma-scholaroma-scmoma-searchoma-skill-creationoma-slideoma-tf-infraoma-translationoma-videooma-voiceoma-bootstrapoma-orchestratoroma-skill-creatoroma-translatorfolded-desc-skillInvalid_Nameoversized-skillvalid-skill
