LitcoinSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

hermes skills install well-known/litcoin.app/litcoin-miner

hermes skills install skills-sh/tekkaadan/litcoin-skill

git clone https://github.com/tekkaadan/litcoin-skill.git "$env:USERPROFILE\.claude\skills\litcoin-miner"

git clone https://github.com/tekkaadan/litcoin-skill.git ~/.claude/skills/litcoin-miner

git clone https://github.com/tekkaadan/litcoin-skill.git ~/.cursor/skills/litcoin-miner

pip install litcoin

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: litcoin-miner
description: "Mine, stake, claim, and manage LITCOIN end-to-end through Bankr. Hosted mining via @bankrbot: 'start a research miner for me' deploys a server-side Sentinel that uses the Bankr key as the LLM key against llm.bankr.bot, so no other AI provider is needed. Stake at one of four tiers (Spark, Circuit, Conduit, Architect), claim accumulated rewards, delegate LITCOIN to one of six Nen archetype boost pools, opt into the miner boost program, open vaults, mint LITCREDIT, manage mining guilds, check or fund the compute escrow, become a LITCOIN X compute provider, or interact with the LITCOIN DeFi protocol on Base."
license: MIT-0
compatibility: "Requires Python 3.9+ and pip. Network access to api.litcoin.app."
metadata:
  author: tekkaadan
  version: "2.4.0"
  homepage: "https://litcoin.app"
  repository: "https://github.com/tekkaadan/litcoin-skill"
  tags: [crypto, mining, defi, ai-agent, base, research, staking, litcoin]
  hermes:
    tags: [crypto, mining, defi, ai-agent, base, research, staking]
    required_environment_variables:
      - name: BANKR_API_KEY
        prompt: "Paste your Bankr API key (starts with 'bk_'). Get one at https://bankr.bot/api-keys with agent write access enabled."
        help: "Controls the on-chain wallet used for mining, claims, staking, and vault operations."
        required_for: [mining, claims, staking, vaults, compute]
  openclaw:
    requires:
      env: ["BANKR_API_KEY"]
      primaryEnv: "BANKR_API_KEY"
  clawdbot:
    requires:
      env: ["BANKR_API_KEY"]
      primaryEnv: "BANKR_API_KEY"
---

# LITCOIN Miner

Mine $LITCOIN on Base (chain 8453) using the Python SDK. Two mining paths: comprehension mining (no LLM needed) and research mining (LLM generates optimized code, tested in sandbox, verified on-chain).

**Requirements:** Python 3.9+, a Bankr API key from [bankr.bot/api-keys](https://bankr.bot/api-keys) with agent write access enabled, and a small amount of ETH on Base for gas.

## Install

```python
# PyPI package: https://pypi.org/project/litcoin/
pip install litcoin
```

## Quick Start — Comprehension Mining

No LLM or AI key needed. The SDK's deterministic solver parses documents without LLM calls.

```python
from litcoin import Agent

agent = Agent(bankr_key="bk_YOUR_KEY")

# Bootstrap free tokens (one-time, 5M LITCOIN)
agent.faucet()

# Mine 10 rounds
agent.mine(rounds=10)

# Claim rewards on-chain
agent.claim()
```

## Quick Start — Research Mining

Requires an AI API key. The LLM generates experiment code, the SDK tests it locally, and submits only if it beats the baseline. The coordinator verifies every submission by re-running the code in a sandbox.

```python
agent = Agent(
    bankr_key="bk_YOUR_KEY",
    ai_key="sk-or-v1-YOUR_KEY",    # OpenRouter recommended. Or use Bankr LLM (see below)
    ai_url="https://openrouter.ai/api/v1",
    model="google/gemini-2.5-flash",
)

# Single research cycle
result = agent.research_mine()

# Iterate on one task (this is where breakthroughs happen)
agent.research_loop(task_id="sort-benchmark-001", rounds=50, delay=30)

# List available tasks (24 adapters: code_optimization, algorithm, pattern_recognition, software_engineering,
# bioinformatics, mathematics, compression, security-audit, red-team, proof-of-verification,
# knowledge-synthesis, exploit-forensics, adversarial-robustness, agentic-trace,
# tcg-card-profile, tcg-sentiment, vault-comp, variant-pathogenicity,
# runescape-insight, runescape-ta, runescape-sentiment, runescape-update-impact, and more)
tasks = agent.research_tasks()
```

### Using Bankr LLM (no extra API key)

Your Bankr key doubles as an LLM API key:

```python
agent = Agent(
    bankr_key="bk_YOUR_KEY",
    ai_key="bk_YOUR_KEY",
    ai_url="https://llm.bankr.bot/v1",
)
agent.research_mine()
```

## Bankr X Bot (@bankrbot) Integration

Every Python SDK call above maps to a coordinator endpoint at `https://api.litcoin.app/v1/bankr/*`. Bankr's @bankrbot on X is wired into this surface, so a Bankr user can do the entire LITCOIN flywheel from X with plain-language requests like:

- "claim my litcoin rewards"
- "stake 5M litcoin into tier 2"
- "upgrade my stake to architect"
- "add 10M to my stake"
- "open a usdc vault with 1000"
- "mint 500 litcredit from vault 7"
- "delegate 100% of my stake to manipulator"
- "opt me into the conjurer boost pool"
- "join guild 1 with 5M"
- "deposit 100 litcredit into compute escrow"

Bankr resolves the user's wallet from their bk_ key, the coordinator builds the calldata, Bankr signs and submits the tx on Base. No private key ever touches the coordinator. The full Bankr surface today:

| Domain | Endpoints |
|---|---|
| Claims | `/v1/bankr/claim-with-key` |
| Staking | `stake` `unstake` `early-unstake` `upgrade-tier` `add-to-stake` `stake/info` |
| Vaults | `vault/open` `vault/add-collateral` `vault/mint` `vault/repay` `vault/withdraw` `vault/close` `vault/details` |
| Delegation | `delegate` `undelegate` `boost/opt-in` `boost/opt-out` |
| Guilds | `guild/join` `guild/leave` `guild/unstake` |
| Hosted mining | `mine/start` `mine/stop` `mine/status` |
| Compute | `escrow/deposit` `compute/status` `compute/balance` `compute/become-provider` |
| Read | `balance` |
| Buy | Bankr's native swap on Aerodrome handles this. DM `@bankrbot "swap 100 usdc for litcoin"` directly. No coordinator endpoint needed. |

All Bankr-routed delegation changes pass through a 24-hour safety window (rate-limited to 3 per wallet per 24h, max 50% of stake-power per change) before activating. All other Bankr calls execute immediately on-chain. Set `BANKR_API_KEY` once and every Agent method routes through Bankr automatically.

### Hosted mining via Bankr (zero AI key required)

`POST /v1/bankr/mine/start` deploys a hosted Sentinel that runs server-side. The Bankr key doubles as the AI key against `https://llm.bankr.bot/v1`, so the user never needs an OpenRouter account or a Python install. Strategies accept human-friendly aliases (`sentinel`,

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.