notitial/ai-toolkit
A documentation-first knowledge base of AI-assisted development patterns, plus the Claude Code agents, hooks, skills and rules installed from it.
field: Developer tools workflow: PR / code reviewDocsSecurity reviewPlanning & specsGit & commits runs claude in CI
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 notitial/ai-toolkit/.claude ./rig-ai-toolkit # 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 notitial/ai-toolkit/.claude/skills/add-account .claude/skills/add-account $ npx degit notitial/ai-toolkit/.claude/skills/audit-practices .claude/skills/audit-practices $ npx degit notitial/ai-toolkit/.claude/skills/audit-tooling .claude/skills/audit-tooling $ npx degit notitial/ai-toolkit/.claude/skills/cleanup-claude .claude/skills/cleanup-claude $ npx degit notitial/ai-toolkit/.claude/skills/remove-account .claude/skills/remove-account $ npx degit notitial/ai-toolkit/.claude/skills/setup-claude .claude/skills/setup-claude $ npx degit notitial/ai-toolkit/skills/add-build-kit .claude/skills/add-build-kit $ npx degit notitial/ai-toolkit/skills/add-claude-review .claude/skills/add-claude-review $ npx degit notitial/ai-toolkit/skills/adr .claude/skills/adr $ npx degit notitial/ai-toolkit/skills/archive-index .claude/skills/archive-index $ npx degit notitial/ai-toolkit/skills/audit-claude .claude/skills/audit-claude $ npx degit notitial/ai-toolkit/skills/audit-repo .claude/skills/audit-repo $ npx degit notitial/ai-toolkit/skills/claude-review-loop .claude/skills/claude-review-loop $ npx degit notitial/ai-toolkit/skills/eta .claude/skills/eta $ npx degit notitial/ai-toolkit/skills/fable-plan .claude/skills/fable-plan $ npx degit notitial/ai-toolkit/skills/feature-kickoff .claude/skills/feature-kickoff $ npx degit notitial/ai-toolkit/skills/handover .claude/skills/handover $ npx degit notitial/ai-toolkit/skills/prep-compact .claude/skills/prep-compact $ npx degit notitial/ai-toolkit/skills/repo-setup .claude/skills/repo-setup $ npx degit notitial/ai-toolkit/skills/review-gate .claude/skills/review-gate $ npx degit notitial/ai-toolkit/skills/workspace-lock-protocol .claude/skills/workspace-lock-protocol
$ curl -fsSL --create-dirs -o .claude/agents/adr-advisor.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/adr-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/payments-reviewer.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/payments-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-author.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/plan-author.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/notitial/ai-toolkit/main/agents/security-auditor.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 (21)
add-accountaudit-practicesaudit-toolingcleanup-clauderemove-accountsetup-claudeadd-build-kitadd-claude-reviewadrarchive-indexaudit-claudeaudit-repoclaude-review-loopetafable-planfeature-kickoffhandoverprep-compactrepo-setupreview-gateworkspace-lock-protocol
Subagents (6)
| adr-advisor model: sonnet | ADR advisor. Scans Architecture Decision Records to find relevant decisions, detect conflicts with proposed changes, and draft new ADR templates. Read-only — produces analysis, never modifies files. |
| code-reviewer model: sonnet | Skeptical code reviewer. Analyzes staged or recent changes adversarially for logic bugs, silent failures, edge cases, and pattern consistency. Read-only — produces findings, never modifies code. Use p |
| payments-reviewer model: opus | Adversarial reviewer for in-app-purchase and billing changes. Reviews diffs touching Apple IAP/StoreKit, subscriptions, entitlements, paywalls, receipt validation, ownership transfer, or billing acros |
| plan-author model: fable | Drafts an implementation plan.md body from a ticket/goal and an affected-surface map, in the exact canonical shape feature-kickoff defines. Grounds every claim in real files (Read/Grep/Glob + read-onl |
| plan-reviewer model: sonnet | Adversarial reviewer for implementation plans before any code is written. Checks a plan document for acceptance-criteria coverage, unverified assumptions, missing states/edge cases, step ordering, and |
| security-auditor model: opus | Security auditor. Scans code changes for secrets, auth vulnerabilities, OWASP top 10 issues, and PII leakage. Read-only — produces findings with severity and remediation, never modifies code. Use Opus |
Slash commands (1)
/claude-pr-review
Permissions
deny (0)
—
ask (0)
—
allow (5)
Bash(ls *)
Bash(grep *)
Bash(jq *)
Bash(wc *)
Bash(mkdir *)
Similar rigs
MCKRUZ/claude-code-mastery
The definitive Claude Code setup, configuration, and mastery skill — CLAUDE.md engineering, MCP servers, agent teams, hooks, CI/CD, and self-updating knowledge base
Minimalist 1.0k tok · · Q0
maryam-bahrami/claude-code-project-structure
A practical Claude Code project template showcasing best practices for CLAUDE.md, commands, skills, agents, MCP integrations, and team workflows.
Pragmatist 3.0k tok · · Q18
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
Pragmatist 2.0k tok · · Q20
Mathiew82/minimal-claudeness
A minimal, dependency-free meta-harness for Claude Code.
Pragmatist 2.7k tok · · Q20