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/Borda/AI-RigWrote 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/borda/ai-rig/bridge_cc-codex)<a href="https://agentmods.dev/plugins/borda/ai-rig/bridge_cc-codex"><img src="https://agentmods.dev/badge/plugins/borda/ai-rig/bridge_cc-codex/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/borda/ai-rig/bridge_cc-codex"><img src="https://agentmods.dev/badge/plugins/borda/ai-rig/bridge_cc-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bridge 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 yesterday.
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
{
"author": {
"name": "Jiri Borovec",
"url": "https://github.com/Borda/AI-Rig"
},
"description": "bridge_CC-Codex provides bidirectional Claude Code and Codex implementation, advice, review, and approval-bound setup with explicit models, budgets, compact results, no-capture authentication, and recursion safety.",
"homepage": "https://github.com/Borda/AI-Rig",
"keywords": [
"claude-code",
"codex",
"advice",
"implementation",
"review"
],
"license": "Apache-2.0",
"name": "bridge",
"repository": "https://github.com/Borda/AI-Rig",
"skills": "./claude-skills/",
"version": "0.11.1"
}
What it installs
The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 131 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.
- yesterday Changed 6bfc9314d8bc
- 2d ago Changed d799067b1ebe
- 3d ago Changed e5c3d7b228b2
- 4d ago Changed 2db6d530de9c
- 6d ago Changed 2f9a5ced627e
- 9d ago Changed 6a536c92d595
- 12d ago Changed b9d9ce105d6e
- 13d ago Changed b0faf5deb201
- 14d ago Changed 0dfbdc3f2503
- 16d ago First seen · 21 lines scan A b03ac7dc974e
bridge is a plugin published in the GitHub repository Borda/AI-Rig (28 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
fuse-ai-pilot
AI Pilot workflow agents: sniper (code quality), research-expert, explore-codebase, websearch.
rageatc-code-oss
Scale-adaptive software development — TDD, verification, perspective-based review, interface design, and tool capabilities (browser automation, PDFs, YouTube transcripts, local-LLM and Codex delegation).
ccam-cost-guard
Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from the daily trend, surfaces the priciest sessions, estimates savings from cheaper-model routing, and wires up cost alert rules …
ccam-platform
Administer CCAM's Claude Code and Codex configuration explorers, provider-aware history import, backup restore, hook installation, home directories, updates, and MCP server.
review
Deep code review driven by a short interview: read-only reader agents per angle, verified findings, and each point routed to ship, issue, brief or propose.
radin
Cost-optimized agentic workflow stack for solo devs: backlog orchestration (radin-batch, radin-plan, radin-review) plus curated companion tools.