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/zai-one/grok-build-mcpWrote 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/rules/zai-one/grok-build-mcp/grok-mcp)<a href="https://agentmods.dev/rules/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/rules/zai-one/grok-build-mcp/grok-mcp/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/rules/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/rules/zai-one/grok-build-mcp/grok-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
grok-mcp 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 7d 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
grok-delegate
Grok = worker. Host = orchestrator/verifier. Unofficial; auth is grok login only.
- Cheap loop:
session_begin→session_nextuntildone→session_end. - Execute card = full
task(objective,project_root,correlation_id,expected_artifacts,test_commands). Poll card ={job_id}only. Never putsession_idon poll. - Card/schema failure → typed consult → execute → poll → review.
- Unpin is default (
GROK_DELEGATE_EXPECTED_AGENT_VERSIONopt-in). Mismatch warns; do not block. - Worktrees
grok/*only. Never push/merge from the bridge. No secrets in receipts or commits. - If
bridge_versionis stale:git pull,pip install -e ., restart MCP. - Tests:
py -3 -m pytest tests -q. No force-push, no--no-verify, no CLI version pin.
Details: AGENTS.md.
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.
- 7d ago First seen · 19 lines · 253 tokens per session scan A 87d8ac565152
grok-mcp is a cursor rule published in the GitHub repository zai-one/grok-build-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 per session on Opus 5. 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 2026-08-31.
Other cursor rules, from other repositories
project-overview
Project overview and architecture reference.
typescript-conventions
TypeScript coding conventions and style guidelines.
development-workflow
Development workflow and common commands.
tools-and-agent
Guidelines for the agent system and tool implementations.
react-ink-components
Guidelines for React components using Ink for terminal UI.
cx-devassist-kics
Scan and remediate IaC (Infrastructure-as-Code) misconfigurations in Dockerfile, Terraform, Kubernetes YAML, and other IaC files using Checkmarx KICS and the Checkmarx MCP imageRemediation tool.