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/okisdev/claude-code-fusionWrote 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/okisdev/claude-code-fusion/grok)<a href="https://agentmods.dev/plugins/okisdev/claude-code-fusion/grok"><img src="https://agentmods.dev/badge/plugins/okisdev/claude-code-fusion/grok/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/plugins/okisdev/claude-code-fusion/grok"><img src="https://agentmods.dev/badge/plugins/okisdev/claude-code-fusion/grok.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
grok 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 today.
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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "grok",
"displayName": "Grok Companion",
"version": "0.0.65",
"description": "Local Grok CLI delegation: task, review, resumable history, background jobs, stats, and setup health checks.",
"author": {
"name": "Harry Yep"
},
"homepage": "https://github.com/okisdev/claude-code-fusion",
"repository": "https://github.com/okisdev/claude-code-fusion",
"license": "MIT",
"keywords": [
"grok",
"xai",
"delegation",
"code-review",
"orchestration"
],
"userConfig": {
"stop_gate": {
"type": "boolean",
"title": "Stop gate review",
"description": "When Claude Code stops with uncommitted working tree changes, Grok reviews the diff in consult mode and can block the stop with a reason.",
"default": false
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 2 agents travel with it, and installing the plugin installs all of them — 169 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today Changed 1a893c39a0ac
- 2d ago Changed 800cfb26b200
- 17d ago Changed 2d8ea20158a4
- 18d ago Changed 896d5949c790
- 25d ago Changed 8a96cd117278
- 26d ago Changed 1f1e8b84b07e
- 1mo ago Changed 79fdce7e8a5d
- 1mo ago Changed e78ee10d80ee
- 1mo ago First seen · 29 lines scan A 61f2c437da86
grok is a plugin published in the GitHub repository okisdev/claude-code-fusion (3 stars, last pushed yesterday), licensed MIT. 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
ibrahim-plugins marketplace
Official Claude Code plugins by Ibrahim — AI image generation, multi-agent orchestration, and more.
swarm-pi-code-plugin
Portable Pi workflows with durable Host Assistance, discovery, review, and isolated implementation.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
team-shinchan
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
orchestra
Conduct a parallel multi-session sprint: one conductor, several work managers in git worktrees, a file-based mailbox, watchdog supervision, and a clean teardown.
good-bad-ugly
The Good, the Bad and the Ugly — tiered multi-agent orchestration for Claude Code. The Good (brain) plans and verifies, the Bad (judgment executor) handles work needing taste, the Ugly (mechanical executor) does the grunt work — in parallel herdr panes with fenced scopes.