deployer

deployer is a skill for Claude Code from Uniswap/uniswap-ai. It costs 42 tokens per session (4,228 once invoked), scanned A, original, MIT.

A guided deployment workflow for Continuous Clearing Auction smart contracts, which sell tokens through an ongoing auction. It uses a factory contract to create configured auctions.

In plain words
What is it for?
Use it to deploy a configured CCA auction, validate its settings, review the deployment plan, and confirm the required parameters.
Why use it?
It helps prevent unsafe or incomplete deployments by checking the configuration, network factory address, and deployment details before giving commands.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Part of the uniswap-cca plugin — 2 skills, 1 MCP server shipped together

not rated 230repo +1 today A scan Socket: passSnyk: warnSkillSpector: warn 42 tokens original MIT

Good fit Use it to deploy a configured CCA auction, validate its settings, review the deployment plan, and confirm the required parameters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uniswap/uniswap-ai/deployer
Install

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.

Any agent
npx skills add Uniswap/uniswap-ai --skill deployer
Clone the repo
git clone --depth 1 https://github.com/Uniswap/uniswap-ai

Made for: Claude Code.

Or install uniswap-cca, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 deployer

README.md
[![agentmods](https://agentmods.dev/badge/skills/uniswap/uniswap-ai/deployer/github.svg)](https://agentmods.dev/skills/uniswap/uniswap-ai/deployer)
Your own site
<a href="https://agentmods.dev/skills/uniswap/uniswap-ai/deployer"><img src="https://agentmods.dev/badge/skills/uniswap/uniswap-ai/deployer/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 deployer

Your own site · 80×15
<a href="https://agentmods.dev/skills/uniswap/uniswap-ai/deployer"><img src="https://agentmods.dev/badge/skills/uniswap/uniswap-ai/deployer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk warn 11 Mar 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

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 →

  • high Privilege Escalation · line 129
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 134
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 72
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 5
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00042 $0.04228
Opus 5 $0.00021 $0.02114
Sonnet 5 $0.00008 $0.00846
Haiku 4.5 $0.00004 $0.00423

Measured 10d ago against content hash ce50f4135d23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deployer scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read, Glob, Grep, Bash(forge:*), Bash(cast:*), Bash(curl:*), AskUserQuestion
packages/plugins/uniswap-cca/skills/deployer/SKILL.md · 519 lines

How it starts

The opening of the file, as written. The whole thing — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCA Deployment

Deploy Continuous Clearing Auction (CCA) smart contracts using the ContinuousClearingAuctionFactory with CREATE2 for consistent addresses across chains.

Runtime Compatibility: This skill uses AskUserQuestion for interactive prompts. If AskUserQuestion is not available in your runtime, collect the same parameters through natural language conversation instead.

Instructions for Claude Code

When the user invokes this skill, guide them through the CCA deployment process with appropriate safety warnings and validation.

Pre-Deployment Requirements

Before proceeding with deployment, you MUST:

  1. Show educational disclaimer and get user acknowledgment
  2. Validate configuration file if provided
  3. Verify factory address for the target network
  4. Confirm deployment parameters with user

Deployment Workflow

  1. Show Educational Disclaimer (REQUIRED)
  2. Load or Request Configuration
  3. Validate Configuration
  4. Display Deployment Plan
  5. Get User Confirmation
  6. Provide Deployment Commands
  7. Post-Deployment Steps

⚠️ Educational Use Disclaimer

IMPORTANT: Before proceeding with deployment, you must acknowledge:

This tool and all deployment instructions are provided for educational purposes only. AI-generated deployment commands may contain errors or security vulnerabilities.

You must:

  1. Review all configurations carefully before deploying
  2. Verify all parameters (addresses, pricing, schedules) are correct
  3. Test on testnets first before deploying to mainnet
  4. Audit your contracts before deploying with real funds

Use AskUserQuestion to confirm the user acknowledges these warnings before proceeding with deployment steps.

Input Validation Rules

Before interpolating ANY user-provided value into forge/cast commands or deployment scripts:

  • Ethereum addresses: MUST match ^0x[a-fA-F0-9]{40}$ — reject otherwise
  • Chain IDs: MUST be from the supported chains list (1, 130, 1301, 8453, 42161, 11155111)
  • Numeric values (supply, prices, blocks, chain IDs): MUST be non-negative and match ^[0-9]+\.?[0-9]*$
  • RPC endpoint URL ($RPC_URL): MUST be https://-scheme and MUST NOT contain any metacharacter or whitespace from the rule below. This value does not come from the configuration file, the user supplies it during the walkthrough, and it reaches --rpc-url on every forge script, cast send, and forge verify-contract command below. "It came from the user, not the config" is not an exemption. Validate it the first time it is supplied, assign it to $RPC_URL, and reference only that variable afterwards; never re-read a raw URL into a later command. An endpoint whose URL needs a query string (a provider API key, for example) is exported into the environment out of band and referenced as $RPC_URL, never pasted into command text.
  • REJECT any input containing shell metacharacters or whitespace: ;, |, &, $, `, (, ), >, <, \, ', ", spaces, tabs, newlines. $(...) and backticks execute even inside double quotes, and a space splits one value into extra forge/cast flags, so neither is ever safe to interpolate. Abort and report which value and which character failed rather than stripping the offending characters and continuing.
  • Never pass raw user input directly to shell commands without validation
  • Always double-quote every interpolation in a generated command (write --rpc-url "$RPC_URL", never the bare unquoted form). Quoting is the second layer, not the first: validate the value before it reaches the command, then quote it as well.

Read the full file on GitHub · 519 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. 10d ago First seen · 519 lines · 42 tokens per session scan A ce50f4135d23

Subscribe to this mod's changes

deployer is a skill published in the GitHub repository Uniswap/uniswap-ai (230 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 4,228 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.