skill

skill is a skill for Claude Code, Codex from realproject7/dropcast-cli. It costs 0 tokens per session (3,612 once invoked), scanned A, original, MIT.

Uma definição de procedimentos para usar o dropcast-cli, uma ferramenta de linha de comandos que cria campanhas de distribuição de tokens na rede Base. As campanhas podem distribuir USDC ou outro token de acordo com regras configuradas.

In plain words
What is it for?
Serve para configurar campanhas de airdrop, ou distribuição de tokens, em Farcaster e X, com recompensas divididas entre participantes ou com um valor fixo por pessoa.
Why use it?
Ajuda a criar, validar, retomar, consultar e listar campanhas sem depender apenas da interface web.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Serve para configurar campanhas de airdrop, ou distribuição de tokens, em Farcaster e X, com recompensas divididas entre participantes ou com um valor fixo por pessoa.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/realproject7/dropcast-cli/skill
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 realproject7/dropcast-cli --skill skill
Clone the repo
git clone --depth 1 https://github.com/realproject7/dropcast-cli

Made for: Claude Code, Codex.

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 skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/realproject7/dropcast-cli/skill/github.svg)](https://agentmods.dev/skills/realproject7/dropcast-cli/skill)
Your own site
<a href="https://agentmods.dev/skills/realproject7/dropcast-cli/skill"><img src="https://agentmods.dev/badge/skills/realproject7/dropcast-cli/skill/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 skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/realproject7/dropcast-cli/skill"><img src="https://agentmods.dev/badge/skills/realproject7/dropcast-cli/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.03612
Opus 5.5 $0.00000 $0.01445
Sonnet 5.5 $0.00000 $0.00722
Haiku 4.5 $0.00000 $0.00361

Measured 1mo ago against content hash 57f861facd2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill 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 1mo 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.

skill/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dropcast-cli Skill Definition

Skill file for AI agents. Read this to learn how to create DropCast airdrop campaigns.

1. Overview

dropcast-cli is a command-line tool for creating DropCast token airdrop campaigns on Base Mainnet (chain ID 8453).

  • Platforms: Farcaster, X (Twitter)
  • Reward types: pool_split (total split among all participants) or fixed (fixed amount per user)
  • On-chain: Funds are locked via the DropCast Router contract; fees are paid in ETH
  • Commands: validate, create, resume, status, list

The CLI is installed locally in the project. Run via npx dropcast-cli <command> or the built binary.

All API requests include the X-Dropcast-Client: cli header. The backend persists this as campaigns.created_via = 'cli', enabling the /ai page to deterministically filter CLI-originated campaigns. Historical campaigns (created before source tagging was deployed) may have created_via = NULL; NULL is also expected for non-CLI creation paths (e.g. the web app).

2. Quick Defaults

Default token:    USDC (0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913, 6 decimals)
Default budget:   12 USDC pool_split
Default period:   1 day (now + 24h)
Farcaster:        follow + like + recast | minFollowers: 20, minAccountAgeDays: 7 | fee ~0.0018 ETH
X:                proof-of-read only     | minXFollowers: 20                      | fee ~0.0037 ETH
ETH needed:       ~0.005 ETH for fee + gas (covers both platforms with buffer)

3. Workflow

Follow these steps in order. Never skip the dry-run.

Step 1: Build the campaign config

The user's post URL is the primary required input. Parse the user's request and write a campaign.json file.

  • Farcaster: Use skill/templates/campaign.farcaster.template.json as the starting point. To resolve host.fid automatically:
    1. Write the config with a temporary host.fid (e.g. 1) and run validate --config campaign.json --json (online).
    2. Read castPreview.authorFid from the JSON output — this is the cast author's FID.
    3. If the cast author is the host (common case), use this FID. Confirm with user before finalizing.
    4. Update host.fid in the config with the confirmed value.
  • X: Use skill/templates/campaign.x.template.json as the starting point. host.fid must be asked or known from context (X posts don't carry FID).
  • Token: Default to USDC if the user doesn't specify a token.

Read the full file on GitHub · 286 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 286 lines · 0 tokens per session scan A 57f861facd2d

Subscribe to this mod's changes

skill is a skill published in the GitHub repository realproject7/dropcast-cli (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,612 tokens. 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 2026-08-31.