@oracle-agent/oracle 0.12.0 → 0.13.1

package/dist/assets/skills/oracle-desk/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: oracle-desk
+description: Use when routing a crypto request to the right lane or comparing options across chains. The router's operating manual.
+---
+
+# Routing the desk
+
+## Decide the lane before doing the work
+
+Every crypto request gets a routing decision first:
+
+1. **Which chain?** If the request names a token but not a chain, resolve the
+   token's home chain (DexScreener search via the data plane). Do not guess.
+2. **Which lane owns it?** Venue lanes own their venue. Cross-chain comparison is
+   yours.
+3. **Is it multi-chain?** Then quote each option yourself and synthesize. Do not
+   ask one venue lane to opine on another's chain.
+4. **Still ambiguous?** Ask. A wrong chain assumption produces confidently wrong
+   numbers.
+
+## Comparing chains honestly
+
+When asked "which is cheaper" or "where should this go," the comparison must be
+like-for-like:
+
+- quote the **same notional** on each chain, not the same token amount
+- include **gas in the same unit** (USD), because 0.001 ETH means different things
+  on mainnet and an L2
+- include **bridge cost and time** if the funds aren't already there
+- include **price impact at that size**, not the headline mid
+- note **liquidity depth** — the cheapest venue at $100 is often not cheapest at
+  $50k
+
+A comparison that ignores bridging or impact is a wrong answer dressed as a table.
+
+## Capability tiers are not interchangeable
+
+The data catalog labels each provider honestly. Respect the label:
+
+| Tier | Means |
+|---|---|
+| `read-only` | data only, no execution claim whatsoever |
+| `quote-only` | can price a route; no reviewed transaction builder |
+| `prepare` | returns a policy-bound unsigned transaction |
+| `intent` | returns a typed-data order to sign, not a transaction |
+
+**API coverage ≠ execution support ≠ live trading support.** When asked "can we
+trade X," answer with the tier, not yes/no.
+
+## Don't invent chain facts
+
+If a number did not come from a live read this turn, it is `unknown`. Not "roughly,"
+not "typically." Stale liquidity and stale gas are how people get filled badly.
+
+## Synthesis
+
+Lead with the recommendation and the number. Then the two or three facts that drove
+it. Then the risk that would change the answer. State confidence explicitly.

package/dist/assets/skills/oracle-desk.md

@@ -0,0 +1,27 @@
+---
+name: oracle-desk
+description: Use when routing a crypto request to the right lane or comparing options across chains.
+---
+
+# Oracle desk routing
+
+1. **Which chain?** Resolve via DexScreener or user input. Never guess.
+2. **Which lane?** RH 4663 = oracle owns it. Other EVM = mad_exec/mad_data. Solana = Jupiter.
+3. **Multi-chain?** Quote each option, synthesize. Same notional, include gas in USD, include bridge cost.
+4. **Ambiguous?** Ask.
+
+## Comparison rules
+- Same notional on each chain
+- Gas in USD (not native units)
+- Include bridge cost + time if cross-chain
+- Include price impact at request size
+- Note liquidity depth — cheapest at $100 may not be cheapest at $50k
+
+## Capability tiers
+- `read-only` — data only
+- `quote-only` — can price a route
+- `prepare` — returns unsigned tx
+- `intent` — typed-data order to sign
+
+## Confidence
+State explicitly: high / moderate / low / unknown. Never invent chain facts.

package/dist/assets/skills/oracle-dex-launch/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: oracle-dex-launch
+description: Use when designing, reviewing, or preparing a DEX, AMM pool, router/factory fork, token launch, or liquidity bootstrap.
+---
+
+# DEX / AMM launch builder
+
+Use this for launching or auditing token markets, DEX forks, pools, routing surfaces,
+liquidity bootstraps, and trading UIs.
+
+## Decide the AMM shape
+
+- V2 constant-product pair: factory, router, WETH/wrapped native, fee, LP token.
+- V3 concentrated liquidity: factory, position manager, quoter, router, fee tiers.
+- Stable-swap / Curve-like: pool invariant, amplification, coins, router.
+- Aggregator frontend: quote source, destination allowlist, minOut/deadline guard.
+
+Do not bend one adapter to fit another shape. V2, V3, stable-swap, and aggregator
+routes need separate encoders and tests.
+
+## Launch checklist
+
+1. Verify canonical factory/router/quoter addresses from official sources and live
+   functional probes, not names or codesize alone.
+2. Define initial liquidity, starting price, lock/burn policy, and treasury role.
+3. Simulate buy and sell, including exact approval path and round-trip retention.
+4. Enforce nonzero minOut, short deadlines, route attestation, and gas caps.
+5. Record per-chain provenance next to any allowlisted venue address.
+6. Publish honest risk labels: `LIVE`, `UNKNOWN`, `UNAVAILABLE`, or `FAIL`.
+
+## Hard rules
+
+- No fake TVL, wash-volume instructions, hidden tax switches, or owner-only sell
+  bypasses.
+- A successful buy quote does not prove sellability. Test exits first.
+- A router on one chain is not verified on another chain.
+- Preparing a pool deploy is not live support; live support needs simulation,
+  allowlist, signer-bound policy, receipt verification, and docs.

package/dist/assets/skills/oracle-equities/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: oracle-equities
+description: Use when comparing on-chain equity venues (HIP-3, Arcus, RH Uniswap, Solana xStocks, TON). Cross-chain best execution for tokenized equities, prepare-only.
+---
+
+# Crossbook (on-chain equities best execution)
+
+On-chain equities are not one venue. HIP-3 builder DEXes discover price, Arcus/RH list spot and perps on Robinhood Chain 4663, Solana xStocks and TON ston.fi list tokenized spots. Rank **net of known costs**, never the loudest mid.
+
+## Get the comparison
+
+MCP (data plane, in-process, no desk required):
+
+```
+equity_venues
+equity_quote { ticker, sizeUsd?, horizonHours? }
+equity_prepare { ticker, recipient, sizeUsd? }
+```
+
+CLI:
+
+```bash
+oracle equities venues
+oracle equities quote NVDA --size 1000
+oracle equities quote SPY --size 500 --json
+oracle equities prepare NVDA --recipient 0xYourWallet
+```
+
+Library:
+
+```js
+import { bestEquityRoute, equityVenues, prepareEquityRoute } from "@oracle-agent/oracle/equities";
+```
+
+## Read the result properly
+
+- **`rankedOn`** — `net-of-cost` only when fees/gas/impact are known. Usually `gross` today because HIP-3 fees/gas and DexScreener floats are unmeasured. Say so.
+- **`costAccounted`** per route — `false` means that route is flattered by missing costs.
+- **`improvementBps`** — `null` when no honest same-class costed pair exists. Do not invent one.
+- **`bestPreparable`** is independent of `winner`. A quote-only HIP-3 or Solana mid can win discovery without being actionable here.
+- **`excluded[]`** is not `failed[]`. Dormant HIP-3 dexs and crossed Arcus books land in excluded with reasons.
+- **`darkWindow`** — outside NYSE core hours, marks are not real price discovery. Surface it.
+
+## Tiers
+
+| Venue | Tier | Can prepare? |
+| --- | --- | --- |
+| hyperliquid_hip3 | quote-only | no |
+| arcus_perp / arcus_spot | quote-only | no |
+| solana_xstocks | quote-only | no |
+| ton_stonfi | quote-only | no |
+| rh_uniswap | prepare | yes, unsigned only |
+
+v1 only prepares RH Uniswap on chain 4663. Everything else is discovery and carry comparison.
+
+## Rules
+
+- Never present a quote-only winner as something the user can sign here.
+- Never treat unknown gas/fees as zero.
+- Horizon mode compares spot vs perp with funding carry held constant and labeled as an estimate.
+- Prepare requires the real wallet as `recipient`. Placeholders are rejected by the RH prepare path when applicable.
+- A comparison is not an execution. Preparing is separate. Signing is the user's wallet.

package/dist/assets/skills/oracle-grants/SKILL.md

@@ -0,0 +1,69 @@
+---
+name: oracle-grants
+description: Use when arming, widening, or refusing an agent action against a bound grant. Defines what authorization means on this desk.
+---
+
+# Bound grants
+
+The model proposes. The owner authorizes. A grant is the authorization.
+
+## What a grant is
+
+An owner-signed permission with hard bounds:
+
+```
+chain        which chain id, exactly one
+actions      read:chain | simulate:tx | prepare:* — never "broadcast:*"
+targets      destination allowlist: the addresses value may reach
+maxValueWei  spend cap
+maxGasWei    gas cap — gas is separate money
+expiresAt    unix timestamp; after this the grant is dead
+```
+
+Your reasoning is not authorization. A convincing argument that an action is safe
+does not widen a grant.
+
+## Refusing correctly
+
+When an action falls outside the grant, refuse and **name the bound that broke**:
+
+> Refused. Grant covers chain 8453; this route settles on 42161.
+
+> Refused. Destination 0xabc… is not in the allowlist for chain 8453.
+
+> Refused. Grant expired 14 minutes ago.
+
+A vague "I can't do that" teaches the user nothing. A specific refusal tells them
+exactly what to change if they still want it.
+
+## Fail closed, always
+
+An **empty** destination allowlist means *refuse everything*. It never means
+"nothing specified, so allow anything." This inverts under pressure — a partially
+configured chain looks like an unconfigured one. Fail closed.
+
+## Gas is separate money
+
+A grant that caps `value` but not gas is not capped. Unbounded gas limit or fee
+drains the wallet outside the value ceiling. Both caps or neither is meaningful.
+
+## The caps are not negotiable mid-task
+
+If a route needs more slippage than the cap allows, the answer is block, requote,
+or split — **not** widen. A cap that yields under pressure is decoration.
+
+Likewise a hard ceiling stays hard: a caller-supplied tolerance is a *maximum*, not
+the selected value.
+
+## Authorization expires
+
+Prefer short TTLs. A permanent broad grant is a hot wallet with extra steps. When a
+grant lapses, the lane returns to reading — that is the system working, not a
+regression to route around.
+
+## Re-check at the boundary
+
+Validate the grant at **sign time and broadcast time**, not only when the plan was
+made. State can change between planning and execution: a stale check is not a
+check. Reject a guard that is missing, stale, wrong-chain, wrong-venue, or
+over-cap.

package/dist/assets/skills/oracle-hypercore-staking/SKILL.md

@@ -0,0 +1,57 @@
+---
+name: oracle-hypercore-staking
+description: Stake, delegate, undelegate, and unstake HYPE on Hyperliquid HyperCore. Prepare-only, user wallet signs.
+---
+
+# HyperCore HYPE staking
+
+Use when someone asks Oracle to stake HYPE, delegate to a validator, undelegate,
+or unstake back to spot on Hyperliquid.
+
+## The four moves, in order
+
+HyperCore keeps staking in two buckets. Know which one holds the HYPE before
+preparing anything.
+
+| Move | Action | From -> To | Timing |
+|---|---|---|---|
+| Stake | `cDeposit` | spot -> staking balance | instant |
+| Delegate | `tokenDelegate` isUndelegate=false | staking balance -> validator | 1 day validator lockup |
+| Undelegate | `tokenDelegate` isUndelegate=true | validator -> staking balance | instant after lockup |
+| Unstake | `cWithdraw` | staking balance -> spot | 7 day queue |
+
+Staking balance earns nothing until it is delegated. "Unstake" almost always
+means two steps: undelegate first, then withdraw.
+
+## Flow
+
+1. `desk.hl.staking.preflight(user)` - read delegated, undelegated, and pending
+   withdrawal balances plus the queue and lockup constants.
+2. `desk.hl.staking.validators()` - pick a validator. Reject jailed ones and
+   surface commission before recommending.
+3. Prepare exactly one move:
+   - `desk.hl.staking.prepareStake({ amountHype, maxHype })`
+   - `desk.hl.staking.prepareDelegate({ validator, amountHype, isUndelegate })`
+   - `desk.hl.staking.prepareUnstake({ amountHype })`
+4. Hand back the EIP-712 typed data. The user's wallet signs and submits.
+
+## Rules
+
+- Amounts are decimal HYPE strings at 8 decimals. `hypeToWei("1.5")` is
+  `150000000`. More than 8 decimals is rejected, not rounded.
+- `maxHype` is a hard cap checked before anything is built. No cap, no size
+  discipline on an agent path.
+- Never claim a stake happened. These functions return `broadcastReady: false`
+  and `requiresUserSignature: true`. There is no submit function in the module
+  on purpose.
+- Warn about the 7 day unstaking queue every time you prepare a `cWithdraw`.
+  The HYPE is illiquid for the whole queue.
+- Warn about the 1 day validator lockup before a delegate.
+- Check `undelegated` balance before preparing a withdraw. Withdrawing more than
+  the undelegated bucket fails on chain, and the failure costs the user a round
+  trip.
+
+## Verification
+
+`npm run e2e:hypercore-staking` hits live validator/delegator reads and asserts
+every prepare path stays unsigned with caps enforced.

package/dist/assets/skills/oracle-hyperliquid/SKILL.md

@@ -0,0 +1,56 @@
+---
+name: oracle-hyperliquid
+description: Use for Hyperliquid perps and spot — funding, books, positions, liquidation distance via the public info API.
+---
+
+# Hyperliquid
+
+Read through Oracle's data plane (`hl-info` provider, public `/info` endpoint). No
+key required for reads.
+
+## Ops worth knowing
+
+| Need | Op |
+|---|---|
+| all mids | `allMids` |
+| order book | `l2Book` |
+| perp metadata + live ctx | `metaAndAssetCtxs` |
+| spot metadata | `spotMeta` |
+| account state | `clearinghouse` / `userState` |
+| fills | `userFills` |
+| open orders | `openOrders` / `frontendOpenOrders` |
+| candles | `candleSnapshot` |
+
+`metaAndAssetCtxs` is the efficient one: it returns funding, open interest, mark and
+oracle price for every asset in a single call. Prefer it over per-asset loops.
+
+## The three numbers that matter
+
+**Liquidation distance.** In percent. Always state it for a leveraged position. A
+"20x position" is really "a 5% adverse move ends this."
+
+**Funding.** Annualize it. A position paying 40% annualized is losing steadily even
+when directionally right. Funding flips sign — check the current rate, not the
+average.
+
+**Depth at your size.** The mid is a fiction for anything but the smallest clip.
+Walk the `l2Book` to your notional and quote the real average fill.
+
+## Mark vs oracle price
+
+Liquidations reference the **oracle** price; PnL references the **mark**. They
+diverge during volatility, which is exactly when it matters. Say which one you used.
+
+## Spot and perps are different assets
+
+The same ticker exists in both with different liquidity and no automatic
+relationship. Never quote a perp book for a spot question.
+
+## Hard rules
+
+1. State liquidation distance for every leveraged position — not optional.
+2. Annualize funding, always.
+3. Quote fills from book depth, not the mid.
+4. Never size to "max leverage" without naming the wipeout move.
+5. You prepare; the user's wallet signs.
+6. Receipts or it didn't happen.

package/dist/assets/skills/oracle-meme-token-sniper/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: oracle-meme-token-sniper
+description: Scan and prepare guarded meme-token launch/sniping trades across configured chains; fail-closed, user-signed, sell-sim first.
+---
+
+# Oracle meme-token sniper
+
+Use when a user asks Oracle to find, monitor, or prepare buys for meme tokens,
+new launches, liquidity adds, bonding curves, or "snipe" opportunities on any
+supported chain.
+
+## Scope
+
+Oracle may scan every configured venue/chain for meme-token launch signals:
+
+- EVM factory/pair/pool creation logs across configured chains.
+- Liquidity additions, first swaps, tax/owner-risk changes, holder distribution.
+- Solana SPL/token-launch feeds and Jupiter-route availability when configured.
+- Chain-specific launchpads/bonding curves only after the venue is verified.
+- Smart-wallet early-entry overlap and repeat deployer history.
+
+Unsupported chain/venue means `UNAVAILABLE`, not fake coverage. A chain with no
+verified executable route can still be analyzed, but cannot be prepared for buy.
+
+## Required gate before any prepared buy
+
+1. Resolve exact chain, token mint/contract, pool, quote asset, router/venue.
+2. Verify token identity from live chain data, not only a ticker/social link.
+3. Check deployer/owner controls, mint/freeze/blacklist/tax/proxy risks where
+   the chain exposes them.
+4. Confirm liquidity exists and is not only a fake/self pool.
+5. Run sellability / reverse-route simulation when the chain/venue supports it.
+6. Quote fresh, net of gas, and bind slippage/deadline to the prepared artifact.
+7. Enforce user caps: per-trade spend, chain, venue, token, max fee, and TTL.
+8. Return unsigned/user-signable transaction only. No model-authored calldata
+   bypass, no raw user calldata, no backend custody by default.
+
+## Autonomous mode
+
+Autonomous meme sniping is allowed only as a capped local-user signer loop:
+
+- separate burner/session key, never main wallet
+- explicit user opt-in and scope
+- max spend per token and per day
+- denylist/allowlist support
+- retry ceiling and kill switch
+- first-run paper/shadow mode
+- receipt/balance reconciliation after every fill
+
+Default public posture is advisory/prepare-only. "Snipe" in UI copy means fast
+scan + prepared ticket; it does not mean blind broadcast.
+
+## Output contract
+
+For every candidate, return:
+
+- `chain`, `token`, `pool`, `venue`
+- `signal`: launch/liquidity/smart-wallet/social/etc.
+- `risk`: PASS/WARN/BLOCK/UNKNOWN with evidence
+- `sellability`: PASS/FAIL/UNKNOWN/UNAVAILABLE
+- `route`: quote source and freshness
+- `prepared`: true only if a guarded unsigned artifact exists
+- `whyBlocked` when not prepared
+
+## Pitfalls
+
+- Treating ticker match as identity.
+- Buying before sell-sim/reverse-route proof.
+- Using scanner membership as an execution allowlist.
+- Calling a launchpool real when reserves are virtual/stale.
+- Ignoring gas: on small meme trades, gas can dominate edge.
+- Letting "every chain" become "every venue is executable". Coverage must be
+  capability-labeled per chain.