chainstacklabs/pumpfun-bonkfun-bot is a Solana trading bot that watches pump.fun and letsbonk.fun for newly created tokens, buys them, and sells them according to a configured strategy. It is for people who want to automate token sniping and trading without relying on third-party APIs.
Borrowing it
Nothing to install: this file belongs to chainstacklabs/pumpfun-bonkfun-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chainstacklabs/pumpfun-bonkfun-bot/main/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/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.02838 | $0.02838 |
| Opus 5.5 | $0.01135 | $0.01135 |
| Sonnet 5.5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 201 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, letsbonk.fun and StonkFun. Snipes newly created tokens and exits on a configured strategy. See README.md for setup and configuration.
AGENTS.md is a symlink to this file, so Claude Code, Codex, Cursor and Windsurf read the same guide.
Reference
Deeper notes, kept out of this file so they load only when needed:
| Doc | Read it before |
|---|---|
| docs/pumpfun-protocol.md | touching account layouts, instruction args, fee recipients or quote assets |
| docs/launchlab-protocol.md | touching letsbonk.fun or StonkFun: platform configs, swap accounts, quote assets, transfer fees |
| docs/listeners-and-geyser.md | changing a listener, the geyser stubs or a decoder |
| docs/cookbook-conventions.md | adding or changing anything under cookbook/ |
| docs/regression-tests.md | picking which verifiers your change needs |
Ground rules
- Running a bot with real funds is how a change gets verified, with explicit
approval for that session and after stating what will run and what it costs.
cookbook/and the simulations move no funds but skipbot_runner, config loading, the trader loop, the exit strategy and cleanup, so they cannot close the question. A verification run covers every mode the change reaches — each listener,extreme_fast_modeon and off, eachexit_strategy— and ends with the wallet holding SOL only. - Never touch
.envor print its contents.SOLANA_PRIVATE_KEYis a live key. - Don't commit anything from
logs/; test with a cookbook script beforesrc/.
Layout
src/ bot source — this dir is the import root (see below)
cookbook/ standalone scripts; each runs on its own, no bot config
tests/regression/ one offline verifier per fixed bug; imports src/
tools/ dev harness — simulations, live round trips, benchmarks
bots/ one YAML per bot instance
idl/ vendored Anchor IDLs
logs/ {bot_name}_{timestamp}.log
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.
- 1mo ago Changed · +1 lines · +68 tokens per session 1b0ae3a752bb
- 1mo ago Changed · +1 lines · +25 tokens per session 770cdeb38a97
- 1mo ago Changed · -8 lines · -148 tokens per session fd60f5afc296
- 1mo ago Changed · +2 lines · +33 tokens per session 21e276d162a5
- 1mo ago Changed · +4 lines · +73 tokens per session f60e9e33a683
- 1mo ago Changed · -277 lines · -5,003 tokens per session 09c15749095c
- 1mo ago Changed · -141 lines · -1,689 tokens per session 64b8618f794f
- 1mo ago Changed · +60 lines · +990 tokens per session 6c84db43ef23
- 1mo ago Changed · +160 lines · +2,481 tokens per session 7de1be17a320
- 2mo 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 (1,054 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,838 tokens to every session, about $0.0114 per session on Opus 5.5. 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.
pumpfun-bonkfun-bot CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pumpfun-bonkfun-bot CLAUDE.mdchainstacklabs/pumpfun-bonkfun-bot | Instructions file | 1.1k | yesterday | Apache-2.0 | A | 2,838 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |