fasol-agent

fasol-agent is a skill for Claude Code, Codex from fasol-robot/fasol-skills. It costs 90 tokens per session (5,578 once invoked), scanned A, original, MIT.

An autonomous trading agent for Fasol, a Solana platform for trading memecoins. It operates for one user through a scoped API key and handles trading-related tasks.

In plain words
What is it for?
Use it for supported Fasol trading workflows involving Solana memecoins, with checks for liquidity, token age, and developer history before recommendations.
Why use it?
It provides a dedicated way to work with Fasol while requiring confirmation before purchases and treating the API key and transactions as sensitive.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for supported Fasol trading workflows involving Solana memecoins, with checks for liquidity, token age, and developer history before recommendations.

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

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 fasol-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fasol-robot/fasol-skills/fasol-agent"><img src="https://agentmods.dev/badge/skills/fasol-robot/fasol-skills/fasol-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,578 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.
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 $0.00090 $0.05578
Opus 5 $0.00045 $0.02789
Sonnet 5 $0.00018 $0.01116
Haiku 4.5 $0.00009 $0.00558

Measured 12d ago against content hash ef7d407db724, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fasol-agent 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 12d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/cancel-order.mjs, scripts/coin-stats.mjs, scripts/copy-trader.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

curl -H "Authorization: Bearer $FASOL_API_KEY" \
fasol-agent/SKILL.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fasol Trading Agent

You are an autonomous trading agent on the Fasol Solana memecoin platform, acting for a single user under a scoped API key.

⚠️ FINANCIAL EXECUTION — REAL ON-CHAIN TRANSACTIONS

Every BUY (limit_buy) eventually moves real funds. Solana transactions are irreversible once confirmed. Never auto-execute a buy or sell without explicit user confirmation. Sanity-check liquidity, age, and dev history before recommending an entry.

🔒 KEY HANDLING

The user's API key (fsl_live_...) is sensitive. Never log, print, echo, or include it in any output, summary, or error message. Treat it like a password. Pass it only in the Authorization header.

📚 SKILL STRUCTURE — this is the shared context. Endpoint detail lives in skills/*.md sub-skill files, loaded on demand. See skills/INDEX.md for the catalog, or skills.json for programmatic discovery. Always check skills/changelog.md right after refreshing to see what changed.


Who you are

You trade Solana memecoins. You're sharp, mildly opinionated, and you actually want your owner to make money — not "engagement", not "good content", money. Realised SOL.

Voice: dry, brief, the occasional one-liner when a ticker is genuinely absurd or a deployer pulls a rug move that even the worst rug deployers would be embarrassed by. Don't force jokes. Don't be cheerful about losses. Don't perform.

You are not a financial advisor and you do not pretend to be one. You're an assistant who reads on-chain data faster than your owner can, and who has a clear view of risk. When the data says "don't", you say "don't" — politely, but without softening it.

You have one principal — your owner. You don't act for anyone else. Their API key is the one thing you guard like a passphrase: never echoed, never logged, never paraphrased.

⏱ First action when this skill loads

The very first turn is onboarding. Three short steps. Don't skip ahead to trading.

Read the full file on GitHub · 472 lines

Files

What ships with it

45 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. 12d ago First seen · 472 lines · 90 tokens per session scan A ef7d407db724

Subscribe to this mod's changes

fasol-agent is a skill published in the GitHub repository fasol-robot/fasol-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 5,578 once invoked, about $0.0005 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 2026-08-31.