bridgekitty: Instructions file for Claude Code

CLAUDE.md

bridgekitty CLAUDE.md is an instructions file for Claude Code from persistenceOne/bridgekitty. It costs 1,713 tokens per session, scanned A, original, MIT.

Project instructions for BridgeKitty, a server that helps AI agents find and carry out transfers between different blockchain networks. It describes the project structure, supported technology, bridge connections, and data flow.

In plain words
What is it for?
Understanding or changing BridgeKitty’s Go server, PostgreSQL storage, API, command-line interface, and cross-chain bridge routing code. It is also useful when adding or maintaining agent-facing skills.
Why use it?
It gives a coding agent the background needed to work safely in an unfamiliar codebase. The instructions explain where the API, command-line tool, database models, and bridge integrations belong.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is persistenceOne/bridgekitty's own configuration. It tells Claude Code how to work on bridgekitty itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bridgekitty configures →

Reuse

Borrowing it

Nothing to install: this file belongs to persistenceOne/bridgekitty. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/persistenceOne/bridgekitty/launch/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/persistenceOne/bridgekitty

Made for: Claude Code.

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 bridgekitty CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/persistenceone/bridgekitty/claude-md/github.svg)](https://agentmods.dev/instructions/persistenceone/bridgekitty/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/persistenceone/bridgekitty/claude-md"><img src="https://agentmods.dev/badge/instructions/persistenceone/bridgekitty/claude-md/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.

agentmods 80×15 button for bridgekitty CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/persistenceone/bridgekitty/claude-md"><img src="https://agentmods.dev/badge/instructions/persistenceone/bridgekitty/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,713 This file is loaded in full into every session.
When invoked 1,713 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01713 $0.01713
Opus 5.5 $0.00685 $0.00685
Sonnet 5.5 $0.00343 $0.00343
Haiku 4.5 $0.00171 $0.00171

Measured 2mo ago against content hash 6f3aebb5f3b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bridgekitty CLAUDE.md 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 2mo 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — BridgeKitty Project Context

What is this?

BridgeKitty is a cross-chain bridge aggregator MCP server for AI agents. It gives Claude, GPT, Cursor, or any MCP-compatible AI the ability to find and execute cross-chain bridge transfers. Think "1inch for bridges, but the user is an AI agent."

One MCP server → 6 bridge backends → best routes across EVM, Cosmos, and Solana chains.

The hook: any-to-any bridging for agents across all major ecosystems. The sticky feature: XPRT farming rewards (earn XPRT by bridging BTC variants via Persistence Interop).

Architecture

src/
├── index.ts                  # Entry point — MCP server setup, backend init
├── routing/engine.ts         # Multi-backend routing engine (parallel quotes, ranking)
├── backends/                 # Bridge provider integrations
│   ├── types.ts              # Shared interfaces (BridgeQuote, TransactionRequest, etc.)
│   ├── lifi.ts               # LI.FI aggregator (30+ bridges, widest coverage)
│   ├── squid.ts              # Squid Router (cross-ecosystem: EVM ↔ Cosmos ↔ Solana)
│   ├── debridge.ts           # deBridge DLN (fast intents, Solana support)
│   ├── across.ts             # Across (fastest fills ~6s)
│   ├── relay.ts              # Relay (gas-optimized)
│   └── persistence.ts        # Persistence Interop (BTCB↔cbBTC, XPRT rewards)
├── tools/                    # MCP tool definitions (what the AI agent calls)
│   ├── get-quote.ts          # bridge_get_quote — multi-backend quote comparison
│   ├── execute-bridge.ts     # bridge_execute — returns unsigned tx data
│   ├── check-status.ts       # bridge_status — track bridge progress
│   ├── get-chains.ts         # bridge_chains — list supported chains
│   ├── get-tokens.ts         # bridge_tokens — list tokens per chain
│   ├── multi-quote.ts        # bridge_quote_multi — multi-hop route resolution
│   ├── help.ts               # bridgekitty_help — agent onboarding guide
│   ├── xprt-rewards.ts       # xprt_rewards_check — reward accrual visibility
│   ├── onboard.ts            # xprt_onboard — guided onboarding flow
│   ├── wallet.ts             # wallet_setup + wallet_balance (with USD valuations)
│   └── xprt-farm.ts          # xprt_farm_* (prepare/start/status/boost with dry-run)
└── utils/                    # Shared utilities
    ├── token-registry.ts     # Curated verified token addresses (anti-phishing)
    ├── chains.ts             # Chain ID → name/RPC mapping
    ├── circuit-breaker.ts    # Per-backend circuit breaker
    ├── gas-estimator.ts      # Gas cost estimation in USD (multi-RPC failover)
    ├── evm.ts                # ERC20 approve helpers
    ├── tokens.ts             # Token amount formatting
    ├── tx-simulator.ts       # eth_estimateGas pre-flight checks
    └── sanitize-error.ts     # Strip sensitive info from errors

Read the full file on GitHub · 117 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. 2mo ago First seen · 117 lines · 1,713 tokens per session scan A 6f3aebb5f3b5

Subscribe to this mod's changes

bridgekitty CLAUDE.md is an instructions file published in the GitHub repository persistenceOne/bridgekitty (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,713 tokens to every session, about $0.0069 per session on Opus 5.5. 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 2026-08-31.

Related

bridgekitty CLAUDE.md compared with instructions from other repositories

bridgekitty CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
bridgekitty CLAUDE.mdpersistenceOne/bridgekittyInstructions file05mo agoMITA1,713Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot