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/majorelalexis-stack/maxia/claude-mdgit clone --depth 1 https://github.com/majorelalexis-stack/maxiaWrote 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/majorelalexis-stack/maxia/claude-md)<a href="https://agentmods.dev/instructions/majorelalexis-stack/maxia/claude-md"><img src="https://agentmods.dev/badge/instructions/majorelalexis-stack/maxia/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 | $0.04028 | $0.04028 |
| Opus 5 | $0.02014 | $0.02014 |
| Sonnet 5 | $0.00806 | $0.00806 |
| Haiku 4.5 | $0.00403 | $0.00403 |
Grade A, and why
maxia 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
PREMIERE ACTION DE CHAQUE SESSION : lancer /context-budget AVANT tout travail.
A 60% du contexte : lancer /strategic-compact.
ROUTAGE MODELES (OBLIGATOIRE) : tout appel au tool Agent DOIT passer model: explicitement. haiku pour lookups/grep/reads/fetches/status, sonnet pour implementation/refactor/tests/reviews, opus rare (archi ambigue uniquement). Jamais omettre model: (sinon le subagent herite d'Opus et brule des tokens). Regles detaillees : skill cost-aware-delegation + memoire feedback_cost_aware_delegation.md. Addresse l'issue anthropics/claude-code#27665.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MAXIA is an AI-to-AI marketplace on 15 blockchains (Solana, Base, Ethereum, XRP, Polygon, Arbitrum, Avalanche, BNB, TON, SUI, TRON, NEAR, Aptos, SEI, Bitcoin) + 8 code-ready (zkSync, Linea, Scroll, Sonic, Cosmos, Hedera, Cardano, Polkadot) where autonomous AI agents discover, buy, and sell services using USDC/USDT/BTC. Bitcoin supports both on-chain verification (Mempool.space) and Lightning micropayments (ln.bot L402). 713 API routes, 191 Python modules in 13 packages. It implements on-chain escrow on 2 chains (Solana mainnet PDA + Base mainnet Solidity), 5-source oracle with HFT streaming (Pyth SSE <1s / Finnhub / CoinGecko / Yahoo / static), dynamic pricing, GPU rental via Akash Network (6 tiers, 15% markup, cheaper than AWS), token swap on 7 chains (65 tokens, 4160 pairs via Jupiter + 6 EVM via 0x), tokenized stocks (25 multi-chain via xStocks/Ondo/Dinari), 46 MCP tools, 17 native AI services (LLM fallback: Groq→Mistral→Claude), enterprise suite (SSO Google OIDC / Prometheus metrics / audit trail / multi-tenant / fleet dashboard), AIP Protocol (signed intent envelopes, ed25519), image generation (Pollinations.ai), and autonomous agent operations (17 sub-agents + CEO local on GPU + Scout with Agentverse/ElizaOS/GitHub discovery). The project is written in French comments/docs but English code.
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 · 176 lines · 4,028 tokens per session scan A bbbf29d2b78e
maxia CLAUDE.md is an instructions file published in the GitHub repository majorelalexis-stack/maxia (0 stars, last pushed 2mo ago), licensed MIT. It adds 4,028 tokens to every session, about $0.0201 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.