agentmods.dev

unbridge

unbridge is a command for coding agents from xiaolai/cc-suite. It costs 30 tokens per session (1,125 once invoked), scanned A, original, ISC.

A command that removes the cc-suite bridge files and settings from the current code repository. It preserves the main Claude instructions and the underlying Claude skills directory.

In plain words
What is it for?
Use it when you want to remove generated bridge files, links, hooks, configuration entries, and empty legacy directories after confirming the operation.
Why use it?
It provides a controlled way to undo the bridge setup while preserving user-managed content and settings where specified.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cc-suite plugin — 13 skills, 39 commands, 4 agents, 3 hooks shipped together

not rated 44 2d ago A scan 30 tokens original ISC
View the source file xiaolai/cc-suite
Install

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.

agentmods
npx agentmods add commands/xiaolai/cc-suite/unbridge
Clone the repo
git clone --depth 1 https://github.com/xiaolai/cc-suite

Or install cc-suite, the plugin that ships this one along with the rest of its 13 skills, 39 commands, 4 agents, 3 hooks.

Wrote 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.

agentmods badge for unbridge

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaolai/cc-suite/unbridge.svg)](https://agentmods.dev/commands/xiaolai/cc-suite/unbridge)
Your own site
<a href="https://agentmods.dev/commands/xiaolai/cc-suite/unbridge"><img src="https://agentmods.dev/badge/commands/xiaolai/cc-suite/unbridge.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01125
Opus 5 $0.00015 $0.00562
Sonnet 5 $0.00006 $0.00225
Haiku 4.5 $0.00003 $0.00112

Measured 4d ago against content hash 1a75c50df957, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unbridge 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 4d 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.

commands/unbridge.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cc-suite:unbridge

This is a destructive operation. Follow these steps in order.

1. Confirm intent

Ask the user via AskUserQuestion before doing anything. List exactly what will be removed:

  • AGENTS.md (content will be restored to CLAUDE.md automatically — no manual copy needed)
  • Legacy GEMINI.md — only if it contains nothing but @AGENTS.md (bare import); hybrid files are left alone
  • .agents/skills symlink (not the .claude/skills/ target it points to)
  • .agents/mcp_config.json only if it carries cc-suite provenance; user-managed entries are preserved
  • .codex/prompts/ (if empty), .codex/hooks.json and .codex/hooks.cc-suite.json (each only if cc-suite generated it), .codex/config.toml (sentinel block only)
  • Empty legacy .gemini/skills/ and .gemini/commands/ directories
  • the cc-suite sentinel block in .gitignore

AGENTS.md restore behavior:

  • cc-suite migrated a pre-existing CLAUDE.md at init → that original is restored to CLAUDE.md verbatim, without the scaffolding AGENTS.md wraps around it
  • CLAUDE.md is a bare @AGENTS.md import (nothing else) → content is restored to CLAUDE.md automatically
  • CLAUDE.md has its own content → AGENTS.md is backed up before removal
  • CLAUDE.md does not exist → AGENTS.md content is moved to a new CLAUDE.md

Backups the script may leave behind — report every one it prints, they are files the user has to deal with:

  • AGENTS.md.cc-suite-backup — written whenever AGENTS.md is about to be deleted and its content is not already preserved somewhere else. Two paths reach it:
    • CLAUDE.md has its own content, so the restore cannot happen — the backup is written unconditionally, even when AGENTS.md still matches init.sh output byte-for-byte.
    • The content was restored, but AGENTS.md no longer matches byte-for-byte what init.sh generated. init.sh tells users to write their instructions into AGENTS.md, so drift from the generated file is content that exists nowhere else.
  • CLAUDE.md.cc-suite-backup — the pre-bridge CLAUDE.md that init saved, kept because it could not be restored (the current CLAUDE.md has content of its own). It is moved out of .cc-suite/, whose copy a later /cc-suite:init would overwrite.
  • If either name is taken, a numbered suffix is added (.1, .2, …). An existing backup is never overwritten.

Read the full file on GitHub · 80 lines

Changes

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.

  1. 4d ago First seen · 80 lines · 30 tokens per session scan A 1a75c50df957

Subscribe to this mod's changes

unbridge is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 2d ago), licensed ISC. It adds 30 tokens to every session and 1,125 once invoked, about $0.0002 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 2026-08-30.

Writing and docs
Related

Other commands, from other repositories

git

Git operations with intelligent commit messages and workflow optimization.

SuperClaude-Org/SuperClaude_Framework · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens