Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mrwogu/promptscriptInstalling this writes the configuration, not the program: `code-review-graph` has to be on your PATH already, or the server will not start.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/mrwogu/promptscript/code-review-graph)<a href="https://agentmods.dev/mcp/mrwogu/promptscript/code-review-graph"><img src="https://agentmods.dev/badge/mcp/mrwogu/promptscript/code-review-graph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/mrwogu/promptscript/code-review-graph"><img src="https://agentmods.dev/badge/mcp/mrwogu/promptscript/code-review-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
code-review-graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"code-review-graph": {
"type": "stdio",
"command": "code-review-graph",
"args": [
"serve"
]
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 9 lines scan A af7c95021132
code-review-graph is an MCP server published in the GitHub repository mrwogu/promptscript (387 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
teamspend
Compare AI coding tool spend before and after a migration -- Cursor, Claude Code, GitHub Copilot, OpenCode, and Codex CLI, real numbers pulled from each vendor's own API or local logs, one command, zero runtime dependencies. Runs locally from the teamspend-cli Python package.
ai-quality-gate
🚀 Kill the Junior AI Era. 🤖 Level up AI code to automatically Principal standards. 🛡️ Quality Gate ✨. Runs locally from the ai-quality-gate npm package. Needs 5 environment variables to run.
audit
Score any public GitHub repo 0-100 against the commit.show audit rubric. Runs locally from the commitshow-mcp npm package.
codebugs
MCP server "codebugs" as configured in faxik/codebugs. Runs locally from the codebugs Python package.
grok-mcp
Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host. Runs locally from the grok-cli-mcp npm package.
src-mcp
MCP server for semantic code search and codebase analysis — Treesitter parsing, AST extraction, and embedding-based indexing for any LLM that supports MCP. Runs locally from the src-mcp npm package.