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 anton-abyzov/vskillnpx agentmods add plugins/anton-abyzov/vskill/codex-bridgegit clone --depth 1 https://github.com/anton-abyzov/vskillGrade A, and why
codex-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 2d 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": "codex-bridge",
"description": "Cross-runtime plugin demonstrator — ships one strict-mode SKILL.md (agents-md-author) installable in both Anthropic Claude Code and OpenAI Codex CLI from the same source. Reference implementation for the dual-manifest authoring pattern (.claude-plugin/ + .codex-plugin/).",
"version": "0.1.0",
"author": {
"name": "Anton Abyzov",
"email": "[email protected]",
"url": "https://github.com/anton-abyzov/vskill"
},
"homepage": "https://github.com/anton-abyzov/vskill/tree/main/plugins/codex-bridge",
"repository": "https://github.com/anton-abyzov/vskill",
"license": "MIT",
"keywords": ["codex", "openai", "cross-runtime", "dual-manifest", "agents-md", "claude-md", "interop", "demo"]
}
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.
- 2d ago First seen · 15 lines scan A ed0560a759aa
codex-bridge is a plugin published in the GitHub repository anton-abyzov/vskill (44 stars, last pushed 1mo ago), 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 2026-08-30.
Other plugins, from other repositories
n8n-as-code
Claude Code plugin for n8n-as-code. Adds the n8n-manager and n8n-architect skills and uses the n8nac CLI as its local knowledge/runtime bridge.
specops
Spec-driven development workflow - transforms ideas into structured specifications (requirements, design, tasks) before implementation.
claude-code-plugin
Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.
toolport
Every tool. One port. Connects this agent to your local Toolport gateway: every MCP server you set up in Toolport, exposed through a handful of compact meta-tools instead of hundreds of tool definitions (90% fewer tokens, measured).
harness-eval
Evaluate AI agent setups for best practices, redundancy, security, and cross-component issues.
harness-maker
Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.