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.
curl -O https://raw.githubusercontent.com/revanthrajeev/spendveto/main/CLAUDE.mdgit clone --depth 1 https://github.com/revanthrajeev/spendvetoWrote 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/revanthrajeev/spendveto/claude-md)<a href="https://agentmods.dev/instructions/revanthrajeev/spendveto/claude-md"><img src="https://agentmods.dev/badge/instructions/revanthrajeev/spendveto/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/revanthrajeev/spendveto/claude-md"><img src="https://agentmods.dev/badge/instructions/revanthrajeev/spendveto/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 | $0.07255 | $0.07255 |
| Opus 5.5 | $0.02902 | $0.02902 |
| Sonnet 5.5 | $0.01451 | $0.01451 |
| Haiku 4.5 | $0.00726 | $0.00726 |
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 3d 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 — 63 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 — model tokens, x402/USDC, cards, fiat payouts. Rails move the money; SpendVeto decides whether the agent is allowed to move it — before anything settles. Since v0.29.0 it is also the neutral trust layer between agents and sellers: attestations, federated reputation, an open policy schema.
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 492), 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 461. Publish 492: 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 14-page Console (dashboard/; rebuild the public demo with node scripts/build-console-demo.mjs)
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 start # the spendveto CLI: server on loopback + one-line setup for Claude Code / Codex / SDKs (SPENDVETO_DATA_DIR relocates state)
npm run check-chains # live-RPC drift check of every EVM registry entry (chain id, token, EIP-3009, EIP-712 domain) — network, so NOT in verify
npm run mcp # stdio MCP server — stdout must stay protocol-clean (dotenv quiet:true)
node bin/spendveto.mjs validate [file] [--strict] # lint a policy against spec/policy-v1.schema.json (same validator as the API + action.yml)
node bin/spendveto.mjs rails # which x402 chain-SDK families are installed + the command for the rest (server/optional.js)
npm run verify # 492 e2e assertions; takes 3–4 min (approval timeouts + TTL sleeps)
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.
- 3d ago Changed · +1 lines · +188 tokens per session bb5fc10971e7
- 5d ago Changed · +9 lines · +349 tokens per session ef7b76cf5116
- 8d ago Changed · +4 lines · +653 tokens per session 1051ed718022
- 9d ago Changed · +6 lines · +1,529 tokens per session 6e5e441c1fbd
- 11d ago Changed 1e216dbfd8a9
- 13d ago Changed · +3 lines · +381 tokens per session 06ac098f873e
- 23d ago Changed · +585 tokens per session c4acfd85076f
- 28d ago Changed b4908d2e2062
- 1mo ago Changed · +3 tokens per session e780981feb4f
- 1mo ago First seen · 40 lines · 3,567 tokens per session scan A 78af65c05d5f
spendveto CLAUDE.md is an instructions file published in the GitHub repository revanthrajeev/spendveto (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 7,255 tokens to every session, about $0.0290 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 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.