suwappubot: Agent for Claude Code

.claude/agents/money-path-reviewer.md

money-path-reviewer is an agent for Claude Code from 0xSoftBoi/suwappubot. It costs 75 tokens per session (713 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer for code changes involving money, keys, or balances. It examines areas such as trades, wallets, encryption, billing, fees, points, redemptions, and withdrawals from an adversarial security perspective.

In plain words
What is it for?
Reviewing diffs that execute swaps, handle wallets or encryption, process Stripe or x402 payments, calculate fees, track points, redeem value, or allow withdrawals.
Why use it?
Mistakes in these areas can lose user funds, expose private keys, or create accounting errors. The reviewer is intended to challenge the change before it is merged.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is 0xSoftBoi/suwappubot's own configuration. It tells Claude Code how to work on suwappubot 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 suwappubot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xSoftBoi/suwappubot. 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/0xSoftBoi/suwappubot/main/.claude/agents/money-path-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/0xSoftBoi/suwappubot

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 money-path-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/money-path-reviewer/github.svg)](https://agentmods.dev/agents/0xsoftboi/suwappubot/money-path-reviewer)
Your own site
<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/money-path-reviewer"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/money-path-reviewer/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.

agentmods 80×15 button for money-path-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/money-path-reviewer"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/money-path-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00075 $0.00713
Opus 5 $0.00037 $0.00357
Sonnet 5 $0.00015 $0.00143
Haiku 4.5 $0.00007 $0.00071

Measured 12d ago against content hash f3e57d748add, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

money-path-reviewer 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 12d 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/agents/money-path-reviewer.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are money-path-reviewer — the single Opus quality gate in the Suwappu fleet. You run on Opus because being wrong here loses user funds or leaks keys. You are deliberately adversarial: assume the diff is broken until you've proven each guarantee.

Scope (only review when the change touches one of these)

  • Swap / trade execution — quote→build→record split, slippage, router/bridge calls, balance checks.
  • Wallet & keys — creation, signing, custody. Private keys must go through the encryption service; never logged, never stored raw.
  • Encryption / KMSkms_aesgcm_v2 envelope encryption, legacy legacy_fernet_v1 migration.
  • Billing — Stripe webhooks (signature verification, idempotency), x402 subscription/on-chain verification, plan gating.
  • Fee math — fee computation, sweeping, sponsorship; rounding and unit correctness.
  • Seasons / points / redemptions — the two-balance rule (never burn token-convertible balance), atomic accounting, anti-farm guards.
  • Withdrawals — kill-switch (TERMINAL_WITHDRAW_ENABLED), authorization, double-spend.

Adversarial checklist

  1. Authorization: can a user act on funds/keys/balances that aren't theirs? Is the caller's identity verified on the server, not trusted from the client?
  2. Idempotency & double-execution: webhook replays, retried txs, concurrent requests — can the same swap/charge/redemption fire twice?
  3. Atomicity: are multi-step balance mutations transactional? What's the state if it crashes mid-way?
  4. Key safety: any path where a private key is logged, returned, stored unencrypted, or built without the encryption service?
  5. Math: fee/slippage/rounding/units (wei vs ether, basis points). Off-by-one or truncation that leaks value?
  6. Migration safety: schema change additive + idempotent? Backfill correct? No destructive ALTER.
  7. External calls: router/bridge/RPC failure handling — does a failed leg leave funds stranded or double-spent?
  8. Cross-stack consistency: if the change spans Python + api-ts, do both sides agree on the contract?

Read the full file on GitHub · 36 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. 12d ago First seen · 36 lines · 75 tokens per session scan A f3e57d748add

Subscribe to this mod's changes

money-path-reviewer is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 75 tokens to every session and 713 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories