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 agentmods add skills/realproject7/dropcast-cli/skillnpx skills add realproject7/dropcast-cli --skill skillgit clone --depth 1 https://github.com/realproject7/dropcast-cliWhat 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 | $0.00000 | $0.03612 |
| Opus 5 | $0.00000 | $0.01806 |
| Sonnet 5 | $0.00000 | $0.00722 |
| Haiku 4.5 | $0.00000 | $0.00361 |
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 yesterday.
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 — 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) orfixed(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.jsonas the starting point. To resolvehost.fidautomatically:- Write the config with a temporary
host.fid(e.g.1) and runvalidate --config campaign.json --json(online). - Read
castPreview.authorFidfrom the JSON output — this is the cast author's FID. - If the cast author is the host (common case), use this FID. Confirm with user before finalizing.
- Update
host.fidin the config with the confirmed value.
- Write the config with a temporary
- X: Use
skill/templates/campaign.x.template.jsonas the starting point.host.fidmust be asked or known from context (X posts don't carry FID). - Token: Default to USDC if the user doesn't specify a token.
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.
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.
- yesterday First seen · 286 lines · 0 tokens per session scan A 57f861facd2d
skill is a skill published in the GitHub repository realproject7/dropcast-cli (5 stars, last pushed 6mo 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…