pumpfun-mechanics

pumpfun-mechanics is a skill for Claude Code from agiprolabs/claude-trading-skills. It costs 21 tokens per session (2,544 once invoked), scanned A, original, MIT.

Technical reference for PumpFun, a Solana token-launch platform, including its bonding-curve mathematics, graduation process, and on-chain instruction formats.

In plain words
What is it for?
Use it to analyze new launches, calculate bonding-curve prices and reserves, study graduation events, build trading strategies, or parse PumpFun transactions.
Why use it?
It provides the rules needed to understand token pricing, launch progress, migration events, and parsed blockchain activity.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the trading-skills plugin — 68 skills shipped together

not rated 356repo +12 9d ago A scan Socket: passSnyk: warnSkillSpector: pass 21 tokens original MIT

Good fit Use it to analyze new launches, calculate bonding-curve prices and reserves, study graduation events, build trading strategies, or parse PumpFun transactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agiprolabs/claude-trading-skills/pumpfun-mechanics
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 agiprolabs/claude-trading-skills --skill pumpfun-mechanics
Clone the repo
git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills

Made for: Claude Code.

Or install trading-skills, the plugin that ships this one along with the rest of its 68 skills.

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 pumpfun-mechanics

README.md
[![agentmods](https://agentmods.dev/badge/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics/github.svg)](https://agentmods.dev/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics)
Your own site
<a href="https://agentmods.dev/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics"><img src="https://agentmods.dev/badge/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics/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 pumpfun-mechanics

Your own site · 80×15
<a href="https://agentmods.dev/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics"><img src="https://agentmods.dev/badge/skills/agiprolabs/claude-trading-skills/pumpfun-mechanics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,544 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
  • Socket pass 21 Mar 2026
  • Snyk warn 21 Mar 2026
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 $0.00021 $0.02544
Opus 5 $0.00010 $0.01272
Sonnet 5 $0.00004 $0.00509
Haiku 4.5 $0.00002 $0.00254

Measured 12d ago against content hash ac4329fda415, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pumpfun-mechanics 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/curve_calculator.py, scripts/parse_events.py), 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.

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.

skills/pumpfun-mechanics/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PumpFun Mechanics — Bonding Curves, Graduation & Instruction Parsing

PumpFun is the dominant Solana token launchpad. Understanding its bonding curve math, graduation process, and instruction formats is essential for analyzing new token launches, building trading strategies around graduation events, and parsing on-chain PumpFun activity.

Bonding Curve Math

PumpFun uses a virtual constant-product (CPMM) bonding curve:

k = virtualSolReserves × virtualTokenReserves

Initial Parameters

Parameter Value
Initial Virtual SOL 30 SOL (30,000,000,000 lamports)
Initial Virtual Tokens ~1.073B tokens (1,073,000,000,000,000 raw, 6 decimals)
Token Total Supply 1B tokens (1,000,000,000,000,000 raw)
Real Token Reserves ~793M tokens (793,000,000,000,000 raw)
Real SOL Reserves 0 (no real SOL at launch)
Fee 1% (applied externally by the program)

Virtual vs Real: Virtual reserves define the curve shape. Real reserves track actual withdrawable funds. The difference (1.073B - 793M = 280M virtual tokens) shapes the initial price but can never be withdrawn.

Spot Price

price_sol_per_token = virtual_sol_reserves / virtual_token_reserves

# In human-readable units:
price = (virtual_sol / 1e9) / (virtual_token / 1e6)

# At genesis: 30 / 1,073,000,000 ≈ 2.796e-8 SOL/token
# At graduation: ~4.1e-7 SOL/token (~14.7x from launch)

Buy Tokens (SOL → Tokens)

def buy_tokens(v_sol: int, v_tok: int, real_tok: int, sol_in: int) -> int:
    """Calculate tokens received for a given SOL input.

    Args:
        v_sol: Virtual SOL reserves (lamports).
        v_tok: Virtual token reserves (raw).
        real_tok: Real token reserves (raw).
        sol_in: SOL to spend (lamports, BEFORE 1% fee).

    Returns:
        Tokens received (raw units).
    """
    k = v_sol * v_tok
    new_v_sol = v_sol + sol_in
    new_v_tok = k // new_v_sol + 1  # +1 matches on-chain rounding
    tokens_out = v_tok - new_v_tok
    return min(tokens_out, real_tok)

Read the full file on GitHub · 267 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. 12d ago First seen · 267 lines · 21 tokens per session scan A ac4329fda415

Subscribe to this mod's changes

pumpfun-mechanics is a skill published in the GitHub repository agiprolabs/claude-trading-skills (356 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 2,544 once invoked, about $0.0001 per session on Opus 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 2026-08-30.