Maksim-Burtsev/merl
Code navigator for the terminal: find your way around a project and review the code agents write. Go to definition and usages without a language server, no config, works over SSH.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Maksim-Burtsev/merl/.claude ./rig-merl # 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 Maksim-Burtsev/merl/.claude/skills/batch .claude/skills/batch $ npx degit Maksim-Burtsev/merl/.claude/skills/groom .claude/skills/groom $ npx degit Maksim-Burtsev/merl/.claude/skills/proposal .claude/skills/proposal $ npx degit Maksim-Burtsev/merl/.claude/skills/smoke-test .claude/skills/smoke-test
$ curl -fsSL --create-dirs -o .claude/agents/merl-finder.md https://raw.githubusercontent.com/Maksim-Burtsev/merl/master/.claude/agents/merl-finder.md $ curl -fsSL --create-dirs -o .claude/agents/merl-implementer.md https://raw.githubusercontent.com/Maksim-Burtsev/merl/master/.claude/agents/merl-implementer.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 (4)
Subagents (2)
| merl-finder model: inherit | One Punchcard finder pass over a merl diff. Implementers and the epic's reviewer start Punchcard's three finders as this type. |
| merl-implementer model: inherit | Builds one task of a merl batch in a worktree the dispatcher made. The batch skill starts every implementer, integrator and fixer as this type. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | "$CLAUDE_PROJECT_DIR"/.claude/hooks/fresh-agents.sh |
Similar rigs
thomwiggers/thom-container
Debian 13 dev container for Apple's container, with chezmoi dotfiles, Claude Code and gh
Minimalist 743 tok · · Q24
ajsahni/agents-office
Agents Office v3 (Beta) — a headless office where AI agents do real work
Pragmatist 4.0k tok · · Q3
aaraujo666/ClaudeCodeSetup
How a Claude Code setup run like a small engineering team works: hooks, tracker, model routing, memory, MCP servers
Minimalist 192 tok · · Q0
stacklok/toolhive-registry-server
Discover, govern and control access to MCP servers and agent skills across your organization
Orchestrator 3.3k tok · · Q0