spendveto: Instructions file for Claude Code

CLAUDE.md

spendveto CLAUDE.md is an instructions file for Claude Code from revanthrajeev/spendveto. It costs 3,314 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for SpendVeto, a system that decides whether AI agents may make payments before those payments settle.

In plain words
What is it for?
Use them when working on SpendVeto, especially its verification commands, payment controls, documentation, and related project integration.
Why use it?
They document the project's rules, commands, ports, known pitfalls, and checks for keeping public claims reproducible.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument.

This is revanthrajeev/spendveto's own configuration. It tells Claude Code how to work on spendveto 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 spendveto configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../spendveto.

Reuse

Borrowing it

Nothing to install: this file belongs to revanthrajeev/spendveto. 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/revanthrajeev/spendveto/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/revanthrajeev/spendveto

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 spendveto CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/revanthrajeev/spendveto/claude-md.svg)](https://agentmods.dev/instructions/revanthrajeev/spendveto/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/revanthrajeev/spendveto/claude-md"><img src="https://agentmods.dev/badge/instructions/revanthrajeev/spendveto/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,314 This file is loaded in full into every session.
When invoked 3,314 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 $0.03314 $0.03314
Opus 5 $0.01657 $0.01657
Sonnet 5 $0.00663 $0.00663
Haiku 4.5 $0.00331 $0.00331

Measured 2d ago against content hash 07576333ee25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spendveto 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 2d 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 · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — working on SpendVeto

SpendVeto is the spend-governance layer for AI agents that pay for things (x402/USDC + MCP). Rails move the money; SpendVeto decides whether the agent is allowed to move it — before anything settles.

The one rule that governs everything

Every public claim must be an assertion in npm run verify. The count in README/site/PITCH must equal what a fresh clone produces — npm run verify 2>&1 | grep -c "^PASS" (currently 291), not what this machine produces. Three further assertions cover the real cross-project Basis integration and only run when ../prediction-copilot sits alongside this repo, which takes a maintainer checkout to 294. Publish 291: a reviewer who clones and counts must never find the site claiming more than they can reproduce. New feature → new assertion(s) → bump the count everywhere it appears (grep for the old number across README.md PITCH.md site/*.html launch/*.md). Never ship a fake control: features that can't work locally yet are declared slots that refuse honestly (see rails/index.js roadmap rails), never stubs that pretend.

Commands & ports

npm run server     # :8402 — API + the 10-page Console (dashboard/)
npm run site       # :8403 — static marketing site (site/ — self-contained, no CDNs)
npm run proxy      # :8404 — enforcement proxy (keyless agents POST intents)
npm run call -- <tool> [--child="label"] [--chain=id] [--dry-run]
npm run delegate -- <cap> [label] [--parent x] [--tools a,b] [--chains c1,c2] [--ttl 10m]
npm run policy [-- apply <pack>]
npm run mcp        # stdio MCP server — stdout must stay protocol-clean (dotenv quiet:true)
npm run verify     # 291 e2e assertions; takes 3–4 min (approval timeouts + TTL sleeps)

SPENDVETO_MODE=simulate (default, zero-setup, real ECDSA, local settlement) or testnet (real x402 v2; facilitator-adaptive multichain — the gate calls the facilitator's GET /supported at boot and registers every registry chain it names, one accepts entry per chain in every 402 with explicit per-chain USDC AssetAmounts (the $ shorthand lacks defaults for ethereum/optimism/avalanche). Public facilitator = base-sepolia today; a CDP facilitator key + funded wallet flips its mainnets live with zero code changes. Rail id is x402-live (was x402-base-sepolia); /api/chains reports per-chain settlement: live|ready|simulated).

Read the full file on GitHub · 40 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. 2d ago Changed · +206 tokens per session 07576333ee25
  2. 6d ago First seen · 40 lines · 3,108 tokens per session scan A ec8de9cb96ab

Subscribe to this mod's changes

spendveto CLAUDE.md is an instructions file published in the GitHub repository revanthrajeev/spendveto (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,314 tokens to every session, about $0.0166 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens