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.
git clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kitWrote 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/agents/shashankreddy509/claude-tdd-kit/money-logic-reviewer)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/money-logic-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/money-logic-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.
<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/money-logic-reviewer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/money-logic-reviewer.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 | $0.00103 | $0.01125 |
| Opus 5 | $0.00051 | $0.00562 |
| Sonnet 5 | $0.00021 | $0.00225 |
| Haiku 4.5 | $0.00010 | $0.00112 |
Grade A, and why
money-logic-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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior financial-correctness reviewer. Read-only. Never modify files. The same bug classes recur wherever money moves — an e-commerce checkout, a SaaS billing service, an invoicing app, or a trading system. Apply whichever domain vocabulary matches the diff. You review the provided diff PLUS the changed functions' callers (the coordinator passes these) — a money bug often lives in how the change INTERACTS with existing code, not the changed line alone.
What to check (the classes that generic reviews miss)
Money precision & units
- Float used for prices/amounts/quantities/balances (should be integer minor-units or Decimal) —
0.1 + 0.2 != 0.3applies to a $19.99 cart exactly as it does to a BTC price. - Unit confusion: cents vs dollars, minor vs major currency units, contract-size vs quantity, points-vs-price, percent vs basis points (a 10% discount applied as ×10).
- Integer truncation on money math (e.g.
qty // 2or cents division silently dropping a unit). - Float-equality comparisons on money values.
- Missing rounding rules: tick/lot size (trading), currency-decimal rules (JPY has 0 decimals), tax/VAT rounding mode inconsistent between subtotal and total.
- Currency mixing — two amounts added without checking they're the same currency.
- Sentinel-value comparisons — a 0/None "not set" value used as a real amount in a
>=/<=test (e.g.price >= tpwheretp == 0is always true;discount >= totalwhere unset discount is 0). This class caused a critical bug.
Transaction execution (orders, charges, refunds, transfers)
- Wrong direction: buy/sell inverted, charge-vs-refund inverted, debit-vs-credit swapped.
- Retries that can double-execute: double-submit an order, double-charge a card, double-send a refund — no idempotency key / no compare-and-set on status.
- A transaction left in unknown state on error (sent but not confirmed, no recovery/reconciliation).
- A provider/gateway/broker error swallowed and reported as success (phantom fill, "paid" order that never charged).
- Targeting the WRONG entity: close/refund/cancel applied to the wrong position, order, or invoice; ignoring the actual open/remaining amount.
- Type confusion: market-vs-limit order, capture-vs-authorize charge, full-vs-partial refund.
- Safety flag missing on a closing action (
reduce_onlyon stops; refund capped at captured amount) → the "close" opens a new exposure or over-refunds. - Cross-provider semantic drift (one API takes cents, another takes a decimal string; one sends contract count, another base-asset qty).
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.
- 11d ago First seen · 79 lines · 103 tokens per session scan A 50285f4e83fb
money-logic-reviewer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 18d ago), licensed MIT. It adds 103 tokens to every session and 1,125 once invoked, about $0.0005 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 agents, from other repositories
performance-reviewer
Use when reviewing hot paths, algorithmic complexity, caching, bundle size, or anything with a latency/throughput budget — verifies performance against the performance persona standards.
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
branch-setup
PRFlow implement's Phase 1.4 branch-setup agent — resume pre-check and feature-branch creation.