blackbearhq/claude-config
BlackBear studio shared Claude Code configuration
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 blackbearhq/claude-config/agents ./rig-claude-config/agents $ npx degit blackbearhq/claude-config/commands ./rig-claude-config/commands $ npx degit blackbearhq/claude-config/skills ./rig-claude-config/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 blackbearhq/claude-config/skills/code-review .claude/skills/code-review $ npx degit blackbearhq/claude-config/skills/db-migration .claude/skills/db-migration $ npx degit blackbearhq/claude-config/skills/deploy-checklist .claude/skills/deploy-checklist $ npx degit blackbearhq/claude-config/skills/glacier-sync .claude/skills/glacier-sync $ npx degit blackbearhq/claude-config/skills/secret-scan .claude/skills/secret-scan $ npx degit blackbearhq/claude-config/skills/stripe-integration .claude/skills/stripe-integration $ npx degit blackbearhq/claude-config/skills/test-gen .claude/skills/test-gen
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/blackbearhq/claude-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/blackbearhq/claude-config/main/agents/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/implement.md https://raw.githubusercontent.com/blackbearhq/claude-config/main/agents/implement.md $ curl -fsSL --create-dirs -o .claude/agents/pr-prep.md https://raw.githubusercontent.com/blackbearhq/claude-config/main/agents/pr-prep.md
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 *)"
]
}
} Skills (7)
Subagents (4)
| architect model: opus | System design and architecture decisions. Use when planning new features, evaluating tradeoffs, or making structural changes across multiple files. |
| explorer model: haiku | Fast codebase exploration, file discovery, and structure analysis. Use for any read-only investigation before making changes. |
| implement model: sonnet | Main TDD implementation agent. Supports three entry modes — card <card_id>, issue <number>, or free-form prompt. Runs in its own git worktree, so several instances can run in parallel safely (dispatch |
| pr-prep model: haiku | Prepares pull request descriptions from git diffs. Use before creating PRs. |
Slash commands (7)
/cost-check/glacier/implement-v/implement/init/skip-tests/triage
Similar rigs
HartBrook/staghorn
Sync Claude Code configs and skills from GitHub — for teams, communities, or across your personal projects. Run evals to verify your guidelines actually work.
Minimalist 196 tok ·
Dipen-Dedania/agent-pulse
Know what your agents are doing
Orchestrator 1.7k tok ·
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok ·
timwuhaotian/the-pair
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.
Pragmatist 5.5k tok ·