apodal-cherry334/code-review-graph
Map code reviews as graphs to optimize token usage and improve analysis accuracy.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~2.7k 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 code-review-graph -- uvx code-review-graph serve $ npx degit apodal-cherry334/code-review-graph/skills ./rig-code-review-graph/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.
$ claude mcp add code-review-graph -- uvx code-review-graph serve $ npx degit apodal-cherry334/code-review-graph/skills/build-graph .claude/skills/build-graph $ npx degit apodal-cherry334/code-review-graph/skills/debug-issue .claude/skills/debug-issue $ npx degit apodal-cherry334/code-review-graph/skills/explore-codebase .claude/skills/explore-codebase $ npx degit apodal-cherry334/code-review-graph/skills/refactor-safely .claude/skills/refactor-safely $ npx degit apodal-cherry334/code-review-graph/skills/review-changes .claude/skills/review-changes $ npx degit apodal-cherry334/code-review-graph/skills/review-delta .claude/skills/review-delta $ npx degit apodal-cherry334/code-review-graph/skills/review-pr .claude/skills/review-pr
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 |
|---|---|---|
| code-review-graph | pypi | 2.5k |
Skills (7)
Similar rigs
tirth8205/code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Pragmatist 6.3k tok · · Q5
shariski/ai-config
Cross-provider AI coding agent configs (opencode + Claude Code + shared). Single source of truth for provider switches. No secrets committed.
Pragmatist 4.4k tok · · Q5
imMamdouhaboammar/get-things-done
Autonomous execution & work modeling engine for AI agents (Claude Code, ChatGPT, Codex, Gemini CLI, Antigravity). Converts fuzzy ideas into verifiable deliverables.
Pragmatist 4.6k tok · · Q15
exactbee/claude-code-workflow
Structured Claude Code workspace — Opus plans, Sonnet executes. Curated MCP stack with ~98% token savings on input. Drop-in template for developers.
Skill Collector 10.0k tok · · Q15