Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ccashwell/evm-cortex --skill uniswap-v4-hooksgit clone --depth 1 https://github.com/ccashwell/evm-cortexWrote 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.
[](https://agentmods.dev/skills/ccashwell/evm-cortex/uniswap-v4-hooks)<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/uniswap-v4-hooks"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/uniswap-v4-hooks/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.
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/uniswap-v4-hooks"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/uniswap-v4-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 394 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.04720 |
| Opus 5.5 | $0.00028 | $0.01888 |
| Sonnet 5.5 | $0.00014 | $0.00944 |
| Haiku 4.5 | $0.00007 | $0.00472 |
Grade A, and why
uniswap-v4-hooks 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uniswap V4 Hook Development
Build against one pinned, compatible dependency graph. Start from a pinned
revision of the Uniswap V4 template or pin v4-core, v4-periphery, and the
hook library to known-compatible revisions. Do not combine examples from
different releases.
As of 2026-02-06 v4-periphery no longer contains BaseHook or HookMiner
(PR #510). Use @openzeppelin/uniswap-hooks (what Uniswap/v4-template pins)
or Uniswap/v4-hooks-public; both expose the same _before*/_after*
internal-override API. HookMiner also remains at
v4-periphery/test/shared/HookMiner.sol.
Before editing, inspect the project's foundry.lock, .gitmodules, and
remappings. Read Hooks.sol, IHooks.sol, PoolOperation.sol, BaseHook.sol,
and HookMiner.sol at those installed revisions. The links at the end are for
discovery; the project's pinned dependency graph is the source of truth.
Architecture
Uniswap V4 keeps pools in a singleton PoolManager. A PoolKey selects one
hook contract or no hook. The same hook contract can serve multiple pools.
The least significant 14 bits of the hook address encode callback permissions.
PoolManager.initialize rejects an invalid hook address, and a maintained
BaseHook validates the deployed address against getHookPermissions() in its
constructor. Deploy a production hook with CREATE2 and a salt mined for the
required low-bit pattern.
In a callback:
msg.senderisPoolManager.- The callback's
senderargument is the immediate caller of the PoolManager operation. It is commonly a router, not the end user. hookDatais caller-controlled unless a trusted integration authenticates and binds it to the operation.
An authentic PoolManager callback does not prove that the pool is authorized.
Anyone can attempt to initialize a PoolKey that names the hook. A hook must
either support permissionless pool creation or validate the complete intended
PoolKey or PoolId. Initialization-sensitive hooks must also validate the
initial price and every other required pool parameter.
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.
- 17d ago Changed · +13 lines 0a5087667469
- 1mo ago First seen · 399 lines · 69 tokens per session scan A 72d1dc882c46
uniswap-v4-hooks is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 18d ago), licensed MIT. It adds 69 tokens to every session and 4,720 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…