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 instructions/chainstacklabs/pumpfun-bonkfun-bot/claude-mdgit clone --depth 1 https://github.com/chainstacklabs/pumpfun-bonkfun-botWrote 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.
[](https://agentmods.dev/instructions/chainstacklabs/pumpfun-bonkfun-bot/claude-md)<a href="https://agentmods.dev/instructions/chainstacklabs/pumpfun-bonkfun-bot/claude-md"><img src="https://agentmods.dev/badge/instructions/chainstacklabs/pumpfun-bonkfun-bot/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.06008 | $0.06008 |
| Opus 5 | $0.03004 | $0.03004 |
| Sonnet 5 | $0.01202 | $0.01202 |
| Haiku 4.5 | $0.00601 | $0.00601 |
Grade A, and why
pumpfun-bonkfun-bot CLAUDE.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
Solana trading bot for pump.fun and letsbonk.fun. Snipes newly created tokens and exits on a configured strategy. See README.md for setup and configuration; this file covers what an agent needs that the code doesn't make obvious.
AGENTS.md is a symlink to this file, so Claude Code, Codex, Cursor, and Windsurf all read the same guide.
Ground rules
- Never run a bot with real funds to test a change. Use
learning-examples/, or the simulation scripts below, which move no funds. - Never touch
.envor print its contents.SOLANA_PRIVATE_KEYis a live key. - Don't commit anything from
logs/. - Test with a learning example before touching
src/.
Layout
src/ bot source — this dir is the import root (see below)
learning-examples/ standalone scripts; each runs on its own, no bot config
bots/ one YAML per bot instance
idl/ vendored Anchor IDLs
logs/ {bot_name}_{timestamp}.log
Imports are rooted at src/, not at the repo. uv pip install -e . puts
src/ itself on sys.path, so it is from core.client import SolanaClient and
from utils.logger import get_logger — not from src.core.... Learning
examples are deliberately self-contained: they import siblings like pump_v2
and tx_status as top-level modules and mostly don't import from src at all.
Don't "fix" an example by rewiring it to import the bot.
Dependency layers, low to high — don't introduce an upward import:
interfaces → utils → core → platforms → monitoring → trading → bot_runner
interfaces is the leaf — it imports nothing internal, and utils/idl_manager.py
imports interfaces.core. geyser holds only generated stubs and likewise
imports nothing internal; cleanup sits on core/utils and is pulled in by
trading.
Platform differences are resolved through interfaces/core.py abstractions
(AddressProvider, curve manager, event parser, instruction builder) and a
registry in platforms/__init__.py. Listeners and the trader are
platform-agnostic (Universal*); anything platform-shaped belongs under
platforms/<name>/.
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.
- 4d ago First seen · 399 lines · 6,008 tokens per session scan A f12989426fb9
pumpfun-bonkfun-bot CLAUDE.md is an instructions file published in the GitHub repository chainstacklabs/pumpfun-bonkfun-bot (976 stars, last pushed 10d ago), licensed Apache-2.0. It adds 6,008 tokens to every session, about $0.0300 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.
Other instructions, from other repositories
bridgenode-skill AGENTS.md
AGENTS.md instructions for bridgenode-ai/bridgenode-skill, covering agents.md — bridgenode skill & examples, what bridgenode is, how an agent pays (x402 flow, 4 steps), quick start (buyer side) and curl — full flow in examples/.
polymarket-alpha-bot AGENTS.md
Instructions for chainstacklabs/polymarket-alpha-bot, a project described as: Find alpha, manage positions in Polymarket.
gmgn-skills CLAUDE.md
Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
mercato-dapp AGENTS.md
Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.
lightning-enable-mcp CLAUDE.md
Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.
x402-stellar-kit AGENTS.md
AGENTS.md instructions for CodeStrux/x402-stellar-kit, covering working with x402-stellar-kit, the one invariant, production seams, bootstrapping accounts across a custody boundary and add x402 to an existing api.