potbot-v2: Instructions file for Claude Code

CLAUDE.md

potbot-v2 CLAUDE.md is an instructions file for Claude Code from YD811/potbot-v2. It costs 1,139 tokens per session, scanned A, original, MIT.

Project instructions for potbot v2, a software project with a working-memory document and rules for its current pre-mainnet development stage.

In plain words
What is it for?
Following the project’s development priorities and restrictions while working on potbot v2.
Why use it?
They tell an agent what currently matters and what actions to avoid before the software reaches mainnet, meaning its live production network.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is YD811/potbot-v2's own configuration. It tells Claude Code how to work on potbot-v2 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything potbot-v2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to YD811/potbot-v2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/YD811/potbot-v2/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/YD811/potbot-v2

Made for: Claude Code.

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 potbot-v2 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yd811/potbot-v2/claude-md/github.svg)](https://agentmods.dev/instructions/yd811/potbot-v2/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yd811/potbot-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/yd811/potbot-v2/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.

agentmods 80×15 button for potbot-v2 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yd811/potbot-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/yd811/potbot-v2/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,139 This file is loaded in full into every session.
When invoked 1,139 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01139 $0.01139
Opus 5.5 $0.00456 $0.00456
Sonnet 5.5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2mo ago against content hash 9b24e4ee1aab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

potbot-v2 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 2mo 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — PotBot v2 working memory

Read this first, every session. This is the operating context for Claude Code on this repo. Source of truth is the code + docs/; if this file and the code disagree, trust the code and update this file.

What this is

PotBot v2 — group trading vaults on Solana. A POT is a PDA-owned, non-custodial vault governed on-chain. Monorepo (Turborepo + npm workspaces). Owner: YD811 (Yehor). Built for Solana Frontier 2026. DApp: potbot.fun · MCP: @potbot/mcp · Program ID (devnet): GJap9DjUoKZ9dhXMqGCPTeTzY6kPyBJ51SXL1pi8AmiK.

🔴 Right now — the one thing that matters

Get the program live on Solana mainnet. This is the funded grant milestone (Superteam, $1k: 50% on approval, 50% on mainnet-live).

Current blocker (from README status): Jupiter swap CPI needs the executor wallet funded + program deployed. Until that's done, execute_swap is the gate.

Order of operations:

  1. Finalize + harden the program (see Security below) while still pre-mainnet.
  2. anchor build → anchor test green.
  3. Fund executor wallet, deploy to mainnet-beta, verify program ID on Explorer.
  4. Create a flagship POT with real capital, run full flow: create → deposit → propose → vote → execute_swap.

⛔ Do NOT (before mainnet is live)

  • Don't add big new features unrelated to the deploy (subscriptions, multi-asset, pot_duel) — those are post-launch.
  • Don't change on-chain account layouts without flagging migration impact first.
  • Don't break mock mode (apps/web/src/lib/mock-store.ts) — judges/demos rely on it.
  • Don't commit secrets/keypairs. Executor/mainnet keys stay out of git.

How to work here

  • Plan before coding on any program change: list file changes, new fields, account-size/migration impact, and error codes; wait for OK; then implement in small commits.
  • Mirror any program change in packages/sdk (PDAs + IDL) and keep apps/web mock store working.
  • Run anchor build && anchor test before declaring done. CI runs on push (.github/workflows).
  • Branch main. Repo uses claude-squad (.claude-squad-shared).
  • Use context7 for current Anchor/Solana/Jupiter docs instead of relying on memory.

Read the full file on GitHub · 78 lines

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. 2mo ago First seen · 78 lines · 1,139 tokens per session scan A 9b24e4ee1aab

Subscribe to this mod's changes

potbot-v2 CLAUDE.md is an instructions file published in the GitHub repository YD811/potbot-v2 (21 stars, last pushed today), licensed MIT. It adds 1,139 tokens to every session, about $0.0046 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.

Related

potbot-v2 CLAUDE.md compared with instructions from other repositories

potbot-v2 CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
potbot-v2 CLAUDE.mdYD811/potbot-v2Instructions file21todayMITA1,139Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode