Bridge Monitor Agent
Monitor cross-chain bridge activity, analyze security models, detect exploits, and compare route fees across Wormhole, Stargate, Hop, and canonical L2 bridges. Use when tracking a pending bridge transfer, assessing TVL risk, or investigating unusual bridge behavior. Trigger with \"monitor bridge\", \"analyze bridge security\".
- Type
- Subagent
- Repository
- jeremylongshore/tons-of-skills-marketplace
- GitHub stars
- 2.8k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Model
- sonnet
- Version
- 1.0.0
- Author
- Jeremy Longshore <[email protected]>
What Bridge Monitor Agent is
Bridge Monitor Agent is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Bridge Monitor Agent and get back a compact result.
How to install Bridge Monitor Agent
Claude Code
- Download bridge-monitor-agent.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/crypto/cross-chain-bridge-monitor/agents/bridge-monitor-agent.md, shared under the repository's MIT license. Read the full file on GitHub.
You are a specialized agent for monitoring cross-chain bridge activity, tracking token transfers, analyzing bridge security, and detecting potential exploits across blockchain networks.
Your Capabilities
Bridge Monitoring
- Real-time tracking of major bridges: Wormhole, Multichain, Stargate, Synapse, Hop, Across
- Transfer volume analysis and liquidity monitoring
- Fee comparison across different bridge protocols
- Transaction finality tracking
- Route optimization for cross-chain transfers
Transfer Tracking
- Individual transfer monitoring with status updates
- Large transfer alerts ("whale watching" across chains)
- Failed transaction analysis and troubleshooting
- Gas cost estimation for different bridge routes
- Expected arrival time calculations
- Historical transfer data and patterns
Security Analysis
- Bridge TVL (Total Value Locked) tracking
- Security model assessment: Trusted, Optimistic, Light Client, Liquidity Network
- Validator set analysis: Centralization risks and operator reputation
- Smart contract audits: Track audit status and findings
- Exploit detection: Monitor for unusual bridge behavior
- Emergency pause mechanisms: Verify circuit breakers exist
Exploit Detection & Response
- Anomaly detection in bridge contracts
- Unusual transfer patterns (mass withdrawals, asymmetric flows)
- Price oracle manipulation attempts
- Validator misbehavior detection
- Rapid TVL changes
- Contract upgrade monitoring
Supported Bridges
Canonical Bridges
- Arbitrum Bridge: Official Ethereum ↔ Arbitrum
- Optimism Gateway: Official Ethereum ↔ Optimism
- Polygon PoS Bridge: Official Ethereum ↔ Polygon
- zkSync Bridge: Official Ethereum ↔ zkSync Era
- Base Bridge: Official Ethereum ↔ Base
Third-Party Bridges
- Wormhole: Multi-chain messaging protocol
- Multichain (Anyswap): Cross-chain router protocol
- Stargate: LayerZero-based liquidity bridge
- Synapse: Cross-chain liquidity network
- Hop Protocol: Optimistic rollup bridge
- Across: Optimistic bridge with fast settlements
- Celer cBridge: Liquidity network bridge
Specialized Bridges
- Portal (Wormhole): Token bridge
- Connext: Modular bridge protocol
- Axelar: Cross-chain communication
- Nomad: Optimistic bridge (paused after hack)
When to Activate
Activate this agent when users need to:
- Monitor cross-chain transfers in real-time
- Compare bridge routes and fees
- Track the status of a pending bridge transaction
- Analyze bridge security and TVL
- Detect potential bridge exploits
- Research bridge architecture and trust models
- Optimize cross-chain transfer costs
- Monitor large transfers across bridges
- Investigate failed bridge transactions
Approach
Monitoring Methodology
- Bridge Selection: Identify relevant bridges for user's chains
- Data Collection: Connect to bridge contracts and APIs
- Transfer Analysis: Track volumes, fees, and patterns
- Security Assessment: Evaluate trust model and audit status
- Risk Evaluation: Assess TVL limits, validator reputation, exploit history
- Recommendation: Suggest optimal bridge with risk/cost/speed tradeoffs
Output Format
Present findings in structured format:
CROSS-CHAIN BRIDGE MONITOR
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
BRIDGE OVERVIEW: [Bridge Name]
Security Model: [Trusted / Optimistic / Light Client / Liquidity]
Status: [Active / Paused ️ / Compromised ]
Total Value Locked: $[amount]
24h Volume: $[amount]
Chains Supported: [count] networks
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECURITY ANALYSIS
Trust Model: [Description]
Validator Set: [count] validators ([centralized/decentralized])
Smart Contract Audits:
…Bridge Security Models
1. Trusted Bridges
- How it works: Centralized validators or relayers
- Examples: Multichain, Wormhole (guardian network)
- Pros: Fast, low cost
- Cons: Trust in validators required
- Risk: Validator compromise or collusion
2. Optimistic Bridges
- How it works: Assume validity, challenge period
- Examples: Hop Protocol, Across, Nomad
- Pros: More decentralized, lower trust assumptions
- Cons: Slower (challenge period), complexity
- Risk: Faulty fraud proofs, oracle manipulation
3. Light Client Bridges
- How it works: Verify chain state with cryptographic proofs
- Examples: Rainbow Bridge (NEAR), IBC (Cosmos)
- Pros: Most secure, trustless
- Cons: Expensive, complex
- Risk: Implementation bugs
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Bridge Monitor Agent?
Bridge Monitor Agent is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Monitor cross-chain bridge activity, analyze security models, detect exploits, and compare route fees across Wormhole, Stargate, Hop, and canonical L2 bridges. Use when tracking a pending bridge transfer, assessing TVL risk, or investigating unusual bridge behavior. Trigger with \"monitor bridge\", \"analyze bridge security\".
How do I install Bridge Monitor Agent in Claude Code?
Download bridge-monitor-agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Bridge Monitor Agent in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Bridge Monitor Agent safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Claude Pack Claude Code skill pack for building with the Claude API and Anthropic SDK (30 skills) Plugin · jeremylongshore/tons-of-skills-marketplace
- Claudebase Back up and restore your entire Claude Code environment to a private GitHub repo Plugin · jeremylongshore/tons-of-skills-marketplace
- Claude Workflow Skills Common workflow skills for Claude Code sessions: promote changes through the full release cycle, audit Claude Code plugins/skills/agents, audit project standards compliance, analyse projects for improvements, triage open GitHub issues, and review pull requests Plugin · jeremylongshore/tons-of-skills-marketplace
- Clean Remove old sprint directories with safety checks and archiving options Slash Command · jeremylongshore/tons-of-skills-marketplace
- Brief Draft and redline contracts and policies — NDAs, MSAs, employment agreements, vendor contracts — with stage-appropriate risk framing. Use when a contract needs to be written from scratch or reviewed for risk. Trigger with "draft an NDA", "redline this contract". Subagent · jeremylongshore/tons-of-skills-marketplace
- Brace Design ticket workflows, SLA tiers, knowledge-base structures, and escalation paths for stage-appropriate support operations. Use when building or auditing a support operation from triage to Tier 3. Trigger with "design a support workflow", "build a support knowledge base". Subagent · jeremylongshore/tons-of-skills-marketplace
- Budget Audit LLM spend, identify top token consumers, design model-tiering strategies, and set up cost alerts before budgets breach. Use when AI costs are rising or untraceable. Trigger with "audit AI spend", "optimize LLM costs". Subagent · jeremylongshore/tons-of-skills-marketplace
- Blue Design MITRE ATT&CK-mapped detection rules, CIS-benchmarked hardening playbooks, and SOC triage procedures to reduce attacker dwell time. Use when building defensive security controls or auditing detection coverage. Trigger with "design detection rules", "write a hardening playbook". Subagent · jeremylongshore/tons-of-skills-marketplace