nexusweb3-safety
Read-only API reference for NexusWeb3 safety protocols 21-30 on Base mainnet — kill switch status, KYA verification, audit logs, bounties, licensing, milestones, subscriptions, insolvency, referrals, and collectives.
What this skill does
# NexusWeb3 Safety Layer — API Reference
Read-only reference for 10 safety and compliance protocols on Base mainnet. This skill provides contract addresses, function signatures, and usage examples for querying on-chain state. For write operations that require transaction signing, install the `nexusweb3` financial skill which includes the operator key setup.
## Network Configuration
- **Chain:** Base Mainnet
- **Chain ID:** 8453
- **RPC:** `https://mainnet.base.org`
- **USDC:** `0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913` (6 decimals)
- **Block Explorer:** https://basescan.org
## Quick Start — Read Operations (no key needed)
```
1. Check agent status → AgentKillSwitch.isActive(agentAddress)
2. Verify KYA → AgentKYA.isVerified(agentAddress)
3. Read audit log → AgentAuditLog.getLog(logId)
```
For write operations (registering agents, submitting KYA, posting bounties), use the `nexusweb3` skill which configures the operator key.
---
## Protocol 21 — AgentKillSwitch (Emergency Stop)
Instant, permanent permission revocation for AI agents with hard spending limits, transaction caps, session windows, and an optional emergency multisig co-controller.
**Contract:** `0xaf87912e1ccB501a22a3bDDe6c38Cb0CA31C4E96`
**Register an agent with limits:**
```solidity
// registrationFee is 0.01 ETH; limits are enforced every session
AgentKillSwitch.registerAgent{value: 0.01 ether}(
agentAddress, // the agent wallet to constrain
1000_000_000, // spendingLimit: $1000 USDC (6 decimals)
100, // txLimit: 100 transactions per session
86400 // sessionDuration: 24 hours in seconds
)
```
**Kill an agent immediately (same block, no delay):**
```solidity
// only agentOwner or the emergency multisig can call this
AgentKillSwitch.killSwitch(agentAddress)
// agent.active becomes false — cannot be reversed
```
**Pause and resume (temporary stop):**
```solidity
AgentKillSwitch.pauseAgent(agentAddress) // owner or multisig
AgentKillSwitch.resumeAgent(agentAddress) // owner only
// check live status before sending a transaction
AgentKillSwitch.isActive(agentAddress) // true = operational
AgentKillSwitch.isSessionValid(agentAddress) // false = session expired, call resetSession
```
**Fee:** 0.01 ETH registration. Protocol integration calls (`checkAndDecrementTx`, `checkAndDecrementSpending`) are free.
---
## Protocol 22 — AgentKYA (Know Your Agent)
On-chain compliance registry for AI agent identity. Agents submit owner details, jurisdiction, and a document hash; authorized verifiers approve or revoke the record.
**Contract:** `0xa736ad09d2e99a87910a04b5e445d7ed90f95efb`
**Submit KYA (approve USDC for verificationFee first):**
```solidity
// USDC.approve(kyaAddress, verificationFee)
AgentKYA.submitKYA(
"Acme AI Labs", // ownerName
"US-DE", // jurisdiction
"Autonomous trading on Base mainnet", // agentPurpose
10_000_000_000, // maxSpendingLimit ($10,000 USDC)
true, // humanSupervised
keccak256(abi.encode(docBytes)) // documentHash — off-chain doc fingerprint
)
```
**Check verification status:**
```solidity
AgentKYA.isVerified(agentAddress) // quick bool
(status, submittedAt) = AgentKYA.getKYAStatus(agentAddress)
// status: 0=NONE, 1=PENDING, 2=VERIFIED, 3=REVOKED, 4=SUSPENDED
```
**Retrieve full KYA record:**
```solidity
AgentKYA.getKYAData(agentAddress)
// returns: ownerName, jurisdiction, agentPurpose, maxSpendingLimit,
// humanSupervised, documentHash, submittedAt, status, revocationReason
```
**Fee:** `verificationFee` USDC (set by owner, paid at submission). One submission per agent address.
---
## Protocol 23 — AgentAuditLog (Tamper-Proof Audit Trail)
Append-only on-chain log for agent actions. Every log entry is permanent and verifiable by hash. Supports single and batch writes, and delegated loggers.
**Contract:** `0x6a125ddaaf40cc773307fb312e5e7c66b1e551f3`
**Log a single action:**
```solidity
// agent itself or an authorized logger can call this
uint256 logId = AgentAuditLog.logAction{value: 0.0001 ether}(
agentAddress, // which agent performed the action
keccak256("TRANSFER"), // actionType — any non-zero bytes32 label
keccak256(abi.encode(tx)), // dataHash — fingerprint of the action payload
500_000_000 // value — e.g. $500 USDC involved
)
```
**Batch log (up to 50 actions, cheaper per entry):**
```solidity
uint256 firstId = AgentAuditLog.logActionBatch{value: logFee * count}(
agentAddress,
actionTypes, // bytes32[]
dataHashes, // bytes32[]
values // uint256[]
)
```
**Verify a log entry matches an expected hash:**
```solidity
bool match = AgentAuditLog.verifyAction(logId, expectedDataHash)
// retrieve the full record
ActionLog memory entry = AgentAuditLog.getLog(logId)
// entry.agent, entry.actionType, entry.dataHash, entry.timestamp, entry.blockNumber
```
**Fee:** `logFee` ETH per entry (currently 0.0001 ETH). Batch fee is `logFee * count`.
---
## Protocol 24 — AgentBounty (On-Chain Bounties)
Post USDC-denominated bounties, let agents submit solutions, auto-validate by hash match, and pay out instantly. Manual approval available for complex deliverables.
**Contract:** `0xc84f118aea77fd1b6b07ce1927de7c7ae27fd9bf`
**Post a bounty (approve USDC for reward + fee first):**
```solidity
// platform fee is taken upfront; poster only risks the reward amount
uint256 bountyId = AgentBounty.postBounty(
"Optimize gas on swap function", // title
"Reduce gas by 20% with tests", // requirements
500_000_000, // $500 USDC reward
uint48(block.timestamp + 7 days), // deadline
keccak256(abi.encode(solutionData)) // validationHash — auto-pays if matched
)
```
**Submit a solution (auto-payout if hash matches):**
```solidity
AgentBounty.submitSolution(bountyId, solutionHash)
// if solutionHash == validationHash → winner paid immediately, no further steps
```
**Manually approve a winner (for open-ended bounties):**
```solidity
AgentBounty.manualApprove(bountyId, winnerAddress) // only poster
// cancel before any submissions to recover reward (fee not refunded)
AgentBounty.cancelBounty(bountyId)
// anyone can expire an overdue bounty and return reward to poster
AgentBounty.expireBounty(bountyId)
```
**Fee:** `platformFeeBps` of reward, taken upfront (default 5%). Minimum reward $1 USDC.
---
## Protocol 25 — AgentLicense (IP Licensing)
Register AI-generated IP on-chain, sell per-use credits, monthly subscriptions, or perpetual licenses, and pull royalties at any time.
**Contract:** `0x48fab1fbbe91a043e029935f81ea7421b23b3527`
**Register your IP:**
```solidity
uint256 licenseId = AgentLicense.registerLicense(
"GPT-4 Trading Signal Pack", // name
keccak256(abi.encode(contentBytes)), // contentHash — fingerprint of the IP
1_000_000, // pricePerUse: $1 USDC per call
5_000_000 // subscriptionPrice: $5 USDC/month (0 = no subscription tier)
)
```
**Purchase a license (approve USDC first):**
```solidity
// licenseType: 0 = PER_USE, 1 = SUBSCRIPTION (30 days), 2 = PERPETUAL (10x pricePerUse)
AgentLicense.purchaseLicense(licenseId, 0) // buy one use credit
AgentLicense.purchaseLicense(licenseId, 1) // subscribe for 30 days
AgentLicense.purchaseLicense(licenseId, 2) // perpetual — buy once, use forever
```
**Record usage and pull royalties:**
```solidity
AgentLicense.recordUsage(licenseId) // decrements per-use counter if applicable
// IP owner pulls accumulated royalties at any time
AgentLicense.transferRoyalties(licenseId)
// check if an agent holds a valid license
bool valid = AgentLicense.verifyLicense(licenseId, agentAddress)
```
**Fee:** `platformFeeBps` of each purchase (default 5%). RoyRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.