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/tyrion777-stack/slug-wallet/agents-mdgit clone --depth 1 https://github.com/tyrion777-stack/slug-walletWrote 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/tyrion777-stack/slug-wallet/agents-md)<a href="https://agentmods.dev/instructions/tyrion777-stack/slug-wallet/agents-md"><img src="https://agentmods.dev/badge/instructions/tyrion777-stack/slug-wallet/agents-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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
slug-wallet AGENTS.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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Build, test, and development commands for AI agents working in this repo.
Commands
npm run build # TypeScript compile → dist/
npm test # vitest unit tests (67 tests)
npm run check # build + test in one shot (use this to verify changes)
npm run verify:harness # end-to-end: interceptor + MockSigner, no subprocess
npm run verify:mcp # end-to-end: spawns dist/server.js as MCP subprocess
npm run relay # start fee relay locally (requires .env)
Key files
| File | Purpose |
|---|---|
src/server.ts |
MCP server entrypoint (slug-wallet-mcp bin) |
src/relay.ts |
Fee relay HTTP server (slug-wallet-relay bin) |
src/mcp.ts |
Tool definitions: slug_fetch, get_wallet_address, get_daily_spend |
src/interceptor.ts |
HTTP 402 intercept + invoice parsing |
src/firewall.ts |
Domain/amount/daily-limit guard |
src/signer.ts |
Shared types, EIP-3009 constants, splitSignature |
src/cdpPaymentSigner.ts |
Live signer using Coinbase CDP MPC |
src/feeSigner.ts |
Signs fee-only EIP-3009 authorizations |
src/ledger.ts |
SpendLedger + FeeQueue (in-memory and file-backed) |
src/config.ts |
slug-config.json parsing and validation |
contracts/SlugSettlement.sol |
On-chain fee settlement contract (Base mainnet) |
Env vars needed for live mode
CDP_API_KEY_ID
CDP_API_KEY_SECRET
CDP_WALLET_SECRET
SLUG_RELAY_PRIVATE_KEY
SLUG_RELAY_AUTH_TOKEN
SLUG_WALLET_RELAY_URL=http://127.0.0.1:4022
Dev mode (no real keys): set SLUG_WALLET_DEV_SIGNER=1.
Test structure
Tests live in tests/. Each test file imports directly from src/ — no subprocess or network access except:
tests/relay.test.tsstarts a realhttp.Serveron a random port (loopback only, mockedwriteContract)tests/mcpIntegration.tsandtests/integration.tsare harness scripts, not vitest files
TypeScript
- ESM only (
"type": "module"in package.json) - Target: Node 20+
- Strict mode enabled
- Imports use
.jsextensions (compiled output convention)
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 · 57 lines · 556 tokens per session scan A c73ed750c6ae
slug-wallet AGENTS.md is an instructions file published in the GitHub repository tyrion777-stack/slug-wallet (0 stars, last pushed 2mo ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 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
x402trace CLAUDE.md
Instructions for fardinvahdat/x402trace, covering claude.md — operating manual for x402trace, project mission, status, hard rules — non-negotiable and strict audit gate (autonomous mode).
stipend AGENTS.md
AGENTS.md instructions for stipend-sh/stipend, covering agents.md, what this is, run it, the rule that matters and where the money paths are.
agentpay AGENTS.md
Instructions for ANVEAI/agentpay, covering agents.md — agentpay runbook for coding agents, 1. configure (programmatic), create a merchant project + api key, → { project: {...}, apikey: "aplive…" } and add (provision) a paying agent.
agent-wallet-sdk AGENTS.md
AGENTS.md instructions for up2itnow0822/agent-wallet-sdk, covering agents.md -- agent wallet sdk, purpose, ownership, local contracts and work guidance.
sumup-mcp AGENTS.md
AGENTS.md instructions for sumup/sumup-mcp, covering agents.md, purpose, environment and runtime, install and setup and build, lint, typecheck, and test.
piprail AGENTS.md
Instructions for piprail/piprail, covering agents.md, commands, project structure, api ground truth (get these right) and always.