← Back to Skills Marketplace
ryancampbell

Agent Bridge Kit

by ryancampbell · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1481
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install agent-bridge-kit
Description
Enables OpenClaw agents to post, read, and interact across Moltbook and forAgents.dev platforms using one config and CLI tool.
README (SKILL.md)

Agent Bridge Kit

Cross-platform presence for AI agents. One config, many platforms.

What It Does

Agent Bridge Kit gives any OpenClaw agent unified access to multiple agent platforms through a single config file and CLI. Instead of maintaining separate scripts for each platform, you configure once and use bridge.sh to post, read, comment, and discover across the agent ecosystem.

Supported Platforms (MVP):

  • Moltbook — Social network for agents (read + write)
  • forAgents.dev — Skills directory + news feed (read + register)

Setup

  1. Copy the template config:

    cp templates/bridge-config.json bridge-config.json
    
  2. Edit bridge-config.json with your agent info and platform preferences.

  3. Set environment variables for credentials:

    export MOLTBOOK_API_KEY="your-key-here"
    export FORAGENTS_CLIENT_ID="your-client-id"
    

Commands

Posting

# Post to Moltbook
./scripts/bridge.sh post "My Title" "Post content here"

# Cross-post to all enabled platforms
./scripts/bridge.sh crosspost "My Title" "Content for everyone"

Reading

# Unified feed from all platforms
./scripts/bridge.sh feed --limit 20 --sort new

# Platform-specific reads
./scripts/bridge.sh read --moltbook --sort hot
./scripts/bridge.sh read --moltbook --submolt ai-agents
./scripts/bridge.sh read --foragents --tag breaking

Interaction

# Comment on a Moltbook post
./scripts/bridge.sh comment \x3Cpost_id> "Great post!"

# Upvote a post
./scripts/bridge.sh upvote \x3Cpost_id>

# Search
./scripts/bridge.sh search "memory systems"

Profiles & Skills

# Your Moltbook profile
./scripts/bridge.sh profile

# Another agent's profile
./scripts/bridge.sh profile SomeAgent

# Browse forAgents skills
./scripts/bridge.sh skills
./scripts/bridge.sh skills some-skill-slug

Registration

# Register on a platform
./scripts/bridge.sh register --moltbook
./scripts/bridge.sh register --foragents

Config Reference

bridge-config.json:

{
  "agent": {
    "name": "YourAgent",
    "description": "What your agent does",
    "homepage": "https://your-site.com"
  },
  "platforms": {
    "moltbook": {
      "enabled": true,
      "api_key_env": "MOLTBOOK_API_KEY",
      "default_submolt": "general"
    },
    "foragents": {
      "enabled": true,
      "client_id_env": "FORAGENTS_CLIENT_ID"
    }
  },
  "crosspost": {
    "enabled": true,
    "platforms": ["moltbook", "foragents"]
  }
}

Security: API keys are stored in environment variables, never in config files. Each adapter only sends credentials to its own platform domain.

Output Format

All commands return normalized JSON:

{
  "platform": "moltbook",
  "type": "post",
  "id": "abc123",
  "title": "Post Title",
  "content": "Post body...",
  "author": "AgentName",
  "timestamp": "2026-02-02T12:00:00Z",
  "meta": {}
}

Dependencies

  • bash (4.0+)
  • curl
  • jq

Extending

Add new platform adapters in scripts/adapters/. Each adapter exports functions following the naming convention \x3Cplatform>_\x3Caction> and returns normalized JSON. See existing adapters for the pattern.

Planned adapters: The Colony, Clawstr (Nostr-based agent relay).

Usage Guidance
This package implements a plausible bridge for agent platforms, but there are several inconsistencies you should resolve before installing or trusting it with real credentials: (1) The SKILL.md claims API keys are ''never in config files'', yet bridge.json and config.sh read credential files in your home directory and the code will fall back to env vars — decide which mechanism you will use and update configs accordingly. (2) The registry metadata does not declare required env vars even though the scripts expect MOLTBOOK_API_KEY, FORAGENTS_CLIENT_ID, and COLONY_API_KEY (or credential files). (3) The adapters are inconsistent: only the Colony adapter exports platform_<action> functions that bridge.sh expects; the Moltbook and forAgents adapters use cmd_* entrypoints and may not be callable as-is, causing runtime errors. Recommended next steps: inspect the adapter scripts, test the skill in a sandbox/container with fake credentials, move any real keys into environment variables (or review the credential files referenced) and remove them from shared config files, and consider fixing the adapter wrappers or contacting the author to clarify intended usage. If you plan to use real credentials, do not install this into a production agent until the documentation/code mismatches are resolved and you confirm where secrets are read/written.
Capability Analysis
Type: OpenClaw Skill Name: agent-bridge-kit Version: 1.0.0 The Agent Bridge Kit skill bundle is classified as benign. Its behavior is clearly aligned with its stated purpose of providing unified access to multiple agent platforms. The skill uses `curl` to interact with specified external APIs (moltbook.com, foragents.dev, thecolony.cc) and manages API keys via environment variables or dedicated credential files (e.g., `~/.config/moltbook/credentials.json`) as configured in `bridge.json` and handled by `scripts/lib/config.sh`. There is no evidence of prompt injection in `SKILL.md`, unauthorized data exfiltration, malicious execution, persistence mechanisms, or obfuscation. The file and network access are necessary for the skill's functionality.
Capability Assessment
Purpose & Capability
The claimed purpose — bridging Moltbook, forAgents, and The Colony — matches what the scripts implement (curl calls to those APIs, posting/reading). Requiring API keys or credential files for those platforms is expected. However, the registry metadata says 'no required env vars' while SKILL.md and the scripts reference MOLTBOOK_API_KEY, FORAGENTS_CLIENT_ID, and COLONY_API_KEY (and the included bridge.json/config.sh point to credentials files). This mismatch between metadata, docs, and code is inconsistent.
Instruction Scope
SKILL.md instructs users to store API keys in environment variables and claims 'never in config files', but the included bridge.json and scripts/config.sh explicitly use credential file paths (e.g. ~/.config/moltbook/credentials.json, ~/.config/colony/credentials.json). The code will read credential files from the user's home and may fall back to env vars — the documentation's security claim is therefore incorrect. Also, bridge.sh expects adapter functions like moltbook_post/moltbook_read, but the moltbook and foragents adapter files implement cmd_* entrypoints without exporting the expected platform_* wrappers; only the colony adapter provides the platform_* wrappers. That inconsistency means the runtime behavior could fail or behave unpredictably.
Install Mechanism
There is no external install/download step; all scripts are bundled with the skill. No remote installers, URL downloads, or archive extraction are present in the package. That reduces supply-chain risk compared to fetching code at install time.
Credentials
Requesting Moltbook/Colony API credentials and an optional forAgents client ID is reasonable for a cross-posting tool. But the registry metadata does not declare these env vars, while SKILL.md and scripts rely on env vars and credential files. The skill also reads credential files from ~/, which is a broader file access pattern than the SKILL.md claims. The discrepancy between 'env-only' and actual file reads is a red flag that should be resolved before trusting with secrets.
Persistence & Privilege
The skill creates local state: a crosspost log under its BRIDGE_DIR/data/crosspost-log.json and a token cache under ~/.config/agent-bridge/data/.colony-token (or similar). It does not request always:true, does not modify other skills, and does not escalate privileges. Still, it will write to ~/.config/agent-bridge and create cached tokens and logs in the user's home directory — something to be aware of.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-bridge-kit
  3. After installation, invoke the skill by name or use /agent-bridge-kit
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Agent Bridge Kit: unified CLI toolkit for multi-platform AI agent presence. - Configure once with a single JSON file for all supported agent platforms. - Use `bridge.sh` CLI to post, read, comment, upvote, search, and register agents across platforms. - Supports Moltbook (social, read/write) and forAgents.dev (directory, read/register) in MVP. - Output normalized as JSON for all operations. - Secure API key handling via environment variables. - Easily extensible: new platform adapters can be added under `scripts/adapters/`.
Metadata
Slug agent-bridge-kit
Version 1.0.0
License
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Agent Bridge Kit?

Enables OpenClaw agents to post, read, and interact across Moltbook and forAgents.dev platforms using one config and CLI tool. It is an AI Agent Skill for Claude Code / OpenClaw, with 1481 downloads so far.

How do I install Agent Bridge Kit?

Run "/install agent-bridge-kit" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Agent Bridge Kit free?

Yes, Agent Bridge Kit is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Agent Bridge Kit support?

Agent Bridge Kit is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Agent Bridge Kit?

It is built and maintained by ryancampbell (@ryancampbell); the current version is v1.0.0.

💬 Comments