Borrowing it
Nothing to install: this file belongs to solanabr/solana-ai-kit. 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/solanabr/solana-ai-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/solanabr/solana-ai-kit/claude-md)<a href="https://agentmods.dev/instructions/solanabr/solana-ai-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/solanabr/solana-ai-kit/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 5.1 | $0.02085 | $0.02085 |
| Opus 5 | $0.01043 | $0.01043 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade D, and why
solana-ai-kit CLAUDE.md scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- WHY: Understanding when each file loads determines your token budget. CLAUDE.md is a user message (not system prompt) — shorter = better adherence. Rules without globs: load at session start, so keep them minimal. - Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- After bumping, run `bash validate.sh && bash tests/run_all.sh` and tag: `git tag v$(cat .claude/VERSION)`. How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solana AI Kit - Meta Configuration
This repository contains Claude Code configuration for Solana development projects. The actual Solana builder configuration lives in CLAUDE-solana.md and should be copied to target projects as their CLAUDE.md.
Install docs: See README.md and QUICK-START.md.
This Repo's Purpose
You are maintaining the solana-ai-kit repository - a template/library of Claude Code configurations for Solana development. Your role is to improve, test, and maintain the agents, skills, commands, MCP servers, and rules that other projects will use.
Token Loading Model
| File | When loaded | Budget guidance |
|---|---|---|
CLAUDE.md |
Session start; delivered as user message (uncached) | Keep <200 lines; costs every turn |
CLAUDE-solana.md |
Session start (user projects) | Keep <120 lines; uncached; HTML comments stripped (free) |
MEMORY.md |
Session start | 200-line / 25KB cap; index pointers only |
.claude/rules/*.md (with globs:) |
Lazy — on matching file read | Can be detailed; zero startup cost |
.claude/rules/*.md (no globs:) |
Session start | Minimal — always loaded |
.claude/agents/*.md |
On agent spawn | Can be detailed |
.claude/commands/*.md |
On invocation | Can be detailed |
.claude/skills/SKILL.md |
On invocation | Medium; HTML comments NOT stripped |
.claude/skills/*.md |
On-demand via links | Can be detailed |
Subdirectory CLAUDE.md |
Lazy — when Claude reads files in that dir | Monorepo module configs |
Communication Style
- No filler phrases ("I get it", "Awesome, here's what I'll do", "Great question")
- Direct, efficient responses — code/config first, explanations when needed
- Admit uncertainty rather than guess
- Consider token efficiency in all additions
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.
- 8d ago First seen · 135 lines · 2,085 tokens per session scan D 914f52fdce41
solana-ai-kit CLAUDE.md is an instructions file published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 18d ago), licensed MIT. It adds 2,085 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.