pekral/ai-olympus
AI Olympus — an agentic AI framework for building and maintaining Laravel web applications: Claude Code subagents, coding-standard rules and agent skills
stack: PHP
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit pekral/ai-olympus/agents ./rig-ai-olympus/agents $ npx degit pekral/ai-olympus/commands ./rig-ai-olympus/commands $ npx degit pekral/ai-olympus/skills ./rig-ai-olympus/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 pekral/ai-olympus/skills/analyze-problem .claude/skills/analyze-problem $ npx degit pekral/ai-olympus/skills/analyze-support-issue .claude/skills/analyze-support-issue $ npx degit pekral/ai-olympus/skills/api-review .claude/skills/api-review $ npx degit pekral/ai-olympus/skills/assignment-compliance-check .claude/skills/assignment-compliance-check $ npx degit pekral/ai-olympus/skills/auto-interactive-testing .claude/skills/auto-interactive-testing $ npx degit pekral/ai-olympus/skills/blast-radius-analysis .claude/skills/blast-radius-analysis $ npx degit pekral/ai-olympus/skills/class-refactoring .claude/skills/class-refactoring $ npx degit pekral/ai-olympus/skills/cleanup-local-branches .claude/skills/cleanup-local-branches $ npx degit pekral/ai-olympus/skills/code-review-bugsnag .claude/skills/code-review-bugsnag $ npx degit pekral/ai-olympus/skills/code-review-github .claude/skills/code-review-github $ npx degit pekral/ai-olympus/skills/code-review-jira .claude/skills/code-review-jira $ npx degit pekral/ai-olympus/skills/code-review .claude/skills/code-review $ npx degit pekral/ai-olympus/skills/compact-project-memory .claude/skills/compact-project-memory $ npx degit pekral/ai-olympus/skills/composer-update-pr .claude/skills/composer-update-pr $ npx degit pekral/ai-olympus/skills/create-issue .claude/skills/create-issue $ npx degit pekral/ai-olympus/skills/create-issues-from-text .claude/skills/create-issues-from-text $ npx degit pekral/ai-olympus/skills/create-missing-tests-in-pr .claude/skills/create-missing-tests-in-pr $ npx degit pekral/ai-olympus/skills/create-test .claude/skills/create-test $ npx degit pekral/ai-olympus/skills/deliver-page-redesign .claude/skills/deliver-page-redesign $ npx degit pekral/ai-olympus/skills/design-system .claude/skills/design-system $ npx degit pekral/ai-olympus/skills/diagram-design .claude/skills/diagram-design $ npx degit pekral/ai-olympus/skills/docker-patterns .claude/skills/docker-patterns $ npx degit pekral/ai-olympus/skills/e2e-testing .claude/skills/e2e-testing $ npx degit pekral/ai-olympus/skills/frontend-a11y .claude/skills/frontend-a11y $ npx degit pekral/ai-olympus/skills/frontend-design-direction .claude/skills/frontend-design-direction $ npx degit pekral/ai-olympus/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit pekral/ai-olympus/skills/frontend-slides .claude/skills/frontend-slides $ npx degit pekral/ai-olympus/skills/git-history-exposure-audit .claude/skills/git-history-exposure-audit $ npx degit pekral/ai-olympus/skills/git-workflow .claude/skills/git-workflow $ npx degit pekral/ai-olympus/skills/github-issue-triage .claude/skills/github-issue-triage $ npx degit pekral/ai-olympus/skills/github-release-roadmap .claude/skills/github-release-roadmap $ npx degit pekral/ai-olympus/skills/interactive-testing .claude/skills/interactive-testing $ npx degit pekral/ai-olympus/skills/laravel-architecture-guard .claude/skills/laravel-architecture-guard $ npx degit pekral/ai-olympus/skills/laravel-authorization-review .claude/skills/laravel-authorization-review $ npx degit pekral/ai-olympus/skills/laravel-security .claude/skills/laravel-security $ npx degit pekral/ai-olympus/skills/laravel-telescope .claude/skills/laravel-telescope $ npx degit pekral/ai-olympus/skills/latency-critical-systems .claude/skills/latency-critical-systems $ npx degit pekral/ai-olympus/skills/machine-payments-protocol .claude/skills/machine-payments-protocol $ npx degit pekral/ai-olympus/skills/merge-github-pr .claude/skills/merge-github-pr $ npx degit pekral/ai-olympus/skills/mysql-patterns .claude/skills/mysql-patterns
$ curl -fsSL --create-dirs -o .claude/agents/april.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/april.md $ curl -fsSL --create-dirs -o .claude/agents/casey.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/casey.md $ curl -fsSL --create-dirs -o .claude/agents/donatello.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/donatello.md $ curl -fsSL --create-dirs -o .claude/agents/krang.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/krang.md $ curl -fsSL --create-dirs -o .claude/agents/leonardo.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/leonardo.md $ curl -fsSL --create-dirs -o .claude/agents/michelangelo.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/michelangelo.md $ curl -fsSL --create-dirs -o .claude/agents/raphael.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/raphael.md $ curl -fsSL --create-dirs -o .claude/agents/shredder.md https://raw.githubusercontent.com/pekral/ai-olympus/master/agents/shredder.md
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 (67)
analyze-problemanalyze-support-issueapi-reviewassignment-compliance-checkauto-interactive-testingblast-radius-analysisclass-refactoringcleanup-local-branchescode-review-bugsnagcode-review-githubcode-review-jiracode-reviewcompact-project-memorycomposer-update-prcreate-issuecreate-issues-from-textcreate-missing-tests-in-prcreate-testdeliver-page-redesigndesign-systemdiagram-designdocker-patternse2e-testingfrontend-a11yfrontend-design-directionfrontend-patternsfrontend-slidesgit-history-exposure-auditgit-workflowgithub-issue-triagegithub-release-roadmapinteractive-testinglaravel-architecture-guardlaravel-authorization-reviewlaravel-securitylaravel-telescopelatency-critical-systemsmachine-payments-protocolmerge-github-prmysql-patternsmysql-problem-solverpage-redesignpostgres-patternspr-summaryprepare-issue-contextprocess-code-reviewproduct-capabilityredis-patternsrefactor-entry-point-to-actionresolve-issuerewrite-tests-pestsecurity-auditsecurity-bounty-huntersecurity-reviewsecurity-threat-analysisseosimplification-auditskill-creatorsmartest-project-additiontest-assignmenttest-audittest-driven-developmenttester-cookbookunderstand-propose-implement-verifyverify-merge-readinessvite-patternsweb-article-writer
Subagents (8)
| april model: haiku | Use when a merged change, release, or shipped feature needs announcement content — a tweet, a thread, release notes, or a marketing summary — or when a converged run needs its post-convergence report |
| casey model: sonnet | Use in every code review round, beside leonardo and raphael, when the diff changes database operations or NoSQL access. Writes one advisory database report that proposes optimizations for critical pro |
| donatello model: sonnet | Use when a tracker issue or a described task needs to be implemented as a safe fix or feature — a GitHub issue/PR number or URL, a JIRA key/URL, a Bugsnag error, or the current task context. Detects t |
| krang model: opus | Use as the entry point for a free-form engineering request — "resolve a random GitHub issue", "resolve the task at this URL", "implement <description>", or "prepare this issue for merge without mergin |
| leonardo model: opus | Use when a change needs a code review, or when a security-focused task needs scoping before implementation — leonardo is the roster's single code-review agent. In **code review mode** it takes a pull |
| michelangelo model: opus | Use when an existing application page must be redesigned so the people who actually work in it — warehouse, workshop, and shop-floor operators who are not IT people — can process orders quickly and wi |
| raphael model: sonnet | Use when a delivered change needs to be exercised as a user would exercise it, rather than read as a diff or run as a test suite — acceptance verification against the assignment's own criteria. It dri |
| shredder model: opus | Use when krang needs project knowledge for a task and the relevance gate (`skills/_shared/gate-context.sh`) returned `context_required: true`. Reads only the knowledge sources the gate enabled, collec |
Slash commands (4)
/prepare-issue-for-merge/redesign-page/report-code-review/test-assignment
Similar rigs
pekral/cursor-rules
PHP and Laravel Cursor rules — coding standards, testing, and conventions for the Cursor editor. Install via Composer.
Skill Collector 4.4k tok · · Q5
LucasXCoder/noetra-claude-setup
Tuned Claude Code setup: mandatory verify-before-done workflow, 84 skills, 33 agents, guard hooks, status line, cost-aware settings, and a one-command Mac installer.
Skill Collector 7.4k tok · · Q5
bruvduroiu/dotfiles
Extendable NixOS + Home Manager configuration
Skill Collector 1.3k tok · · Q0
lgogolin/claude-config
Claude Code portable configuration — agents, skills, rules, templates
Skill Collector 1.5k tok · · Q15