emeraldleaf/okl
Lessons your coding agent can trust: briefed before every task, proven by checks, and flagged when the code they cover changes. Works with Claude Code and any MCP agent.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~4.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add okl -- okl mcp $ npx degit emeraldleaf/okl/.claude ./rig-okl # 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.
$ claude mcp add okl -- okl mcp $ npx degit emeraldleaf/okl/.claude/skills/encoding-loop .claude/skills/encoding-loop $ npx degit <redacted>-before-claiming .claude/skills/verify-before-claiming
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/emeraldleaf/okl/main/.claude/agents/architecture-reviewer.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| okl | binary | 2.5k |
Skills (2)
Subagents (1)
| architecture-reviewer model: inherit | Reviews a diff or a proposed change against this repo's encoded rules and the org knowledge layer. Invoke on non-pattern-conforming changes (new bounded context, novel dependency, security-model chang |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| Stop | * | "$CLAUDE_PROJECT_DIR"/.claude/hooks/stop-okl-encode.sh |
| UserPromptSubmit | * | "$CLAUDE_PROJECT_DIR"/.claude/hooks/userpromptsubmit-okl-check.sh |
Slash commands (1)
/record
Similar rigs
KonixDev/claude-code-guardrails
Architecture rules your AI coding agent can't skip: CLAUDE.md/AGENTS.md, Claude Code hooks, ESLint boundaries, Cursor rules. Copy-in kit.
Minimalist 810 tok · · Q18
TbusOS/android-llm-bridge
让 LLM Agent 直接在线调试安卓设备 —— 抽象 adb / ssh / UART 多种传输,通过 MCP / CLI / Web API 三层接入大模型。
Orchestrator 2.6k tok · · Q0
norton77930/Provost
Classify every request, let cheaper models do the typing, review only on risk: orchestration policy, roles and handoff runtime for Claude Code
Orchestrator 886 tok · · Q0
Tamircohen28/tamirs-superpowers
A portable agent toolkit — 31 skills, 10 specialist agents, worktree hooks and MCP stubs — shipped from one canonical source to six agent surfaces across five platforms: Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI and OpenCode.
Orchestrator 7.0k tok · · Q18