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.
/plugin marketplace add kai-wedekind/claude-code-grok-bridgenpx agentmods add plugins/kai-wedekind/claude-code-grok-bridge/grok-buildgit clone --depth 1 https://github.com/kai-wedekind/claude-code-grok-bridgeWrote 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/plugins/kai-wedekind/claude-code-grok-bridge/grok-build)<a href="https://agentmods.dev/plugins/kai-wedekind/claude-code-grok-bridge/grok-build"><img src="https://agentmods.dev/badge/plugins/kai-wedekind/claude-code-grok-bridge/grok-build.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
grok-build 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 5d 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
{
"name": "grok-build",
"version": "0.3.3",
"description": "Claude Code ↔ Grok Build bridge for review, critique, and delegation.",
"author": {
"name": "Kai Wedekind"
},
"homepage": "https://github.com/kai-wedekind/claude-code-grok-bridge",
"repository": "https://github.com/kai-wedekind/claude-code-grok-bridge"
}
What it installs
The manifest is a name and a version. 3 skills, 7 commands, 1 agent, 2 hooks travel with it, and installing the plugin installs all of them — 272 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill grok-routing A 92 tokens
- Skill grok-delegate-runtime A 20 tokens
- Skill grok-run-output A 18 tokens
- Command critique A 14 tokens
- Command check A 15 tokens
- Command runs A 11 tokens
- Command show A 15 tokens
- Command stop A 11 tokens
- Command delegate A 20 tokens
- Command review A 11 tokens
- Agent grok-delegate A 45 tokens
- Hook SessionStart A not measured
- Hook SessionEnd A not measured
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.
- 5d ago First seen · 11 lines scan A f80d474114a7
grok-build is a plugin published in the GitHub repository kai-wedekind/claude-code-grok-bridge (2 stars, last pushed 14d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
grok
Use Grok Build CLI from Claude Code to review code or delegate tasks.
grok-cc
Delegate and review code with the Grok CLI from Claude Code, like the codex plugin.
grokodex
Use local Grok from Claude Code: delegate tasks, Imagine images, and search X via MCP.
codex
Use the local Codex CLI from Grok Build to review code or delegate tasks.
katalepsis
Verify understanding of a result or artifact through intent-scented entry points — /grasp (κατάληψις: a grasping firmly).
periagoge
Align concrete cases first, then name what they share — /induce (περιαγωγή: turning-around).