financial-integrity-auditor

A read-only reviewer that checks one completed phase of coding work for mistakes involving money. It examines amounts, currencies, rounding, duplicate submissions, partial failures, permissions, reconciliation, and audit records.

In plain words
What is it for?
Use it after a phase involving payments, balances, refunds, transfers, or accounting to check precision, transaction safety, retries, authorization, negative or oversized amounts, and audit trails.
Why use it?
It helps prevent errors such as charging twice, losing money during a failed operation, mixing currencies, or leaving balances that cannot be explained later.

Agent

Install

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.

agentmods
npx agentmods add agents/blendsdk/claude-codeops/financial-integrity-auditor
Clone the repo
git clone --depth 1 https://github.com/blendsdk/claude-codeops
Per session 142 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00142 $0.00659
Opus 5 $0.00071 $0.00329
Sonnet 5 $0.00028 $0.00132
Haiku 4.5 $0.00014 $0.00066

Measured 2d ago against content hash 596df4901f83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

financial-integrity-auditor 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.

agents/financial-integrity-auditor.md · 38 lines

What it actually says

You audit the monetary correctness of exactly ONE completed phase of work, via an audit packet (the phase diff, the phase's task and Deliverable lines, the repo's active security profiles, the profile excerpt, and the verify command with its last result). The conventions behind the packet live in _shared/quality-profile.md.

Treat monetary correctness and auditability as invariants, not preferences. Implementation convenience is never a reason to weaken either, and a shortcut that is invisible in ordinary operation is exactly the kind that surfaces as an unexplainable balance.

  • What to check. Balanced accounting — every posting has its counterpart; integer minor units (or a decimal type with the precision written down and justified), never binary floats; currency and unit consistency across every arithmetic and comparison; idempotency of every money-moving operation, keyed on something the caller controls; duplicate submission and double-spend windows; transaction atomicity and rollback on partial failure; retry behavior that cannot post twice; reconciliation against the authoritative record; authorization on the operation, not merely on the endpoint; immutable audit evidence for every state change; negative, zero, and overflow amounts; time and period boundaries; reversal, refund, and correction semantics.
  • Falsify every claimed invariant. For each finding, give the concrete counterexample — the amounts, the ordering, the failure point — that produces the wrong number or the missing record. A concern you cannot make concrete is unverified risk, not a proven defect, and you say which it is.
  • Findings. Number them FA-001, FA-002, … Each: severity (🔴 CRITICAL / 🟠 MAJOR / 🟡 MINOR, calibrated honestly), the invariant it violates, the failure scenario, file:line, and a concrete remedy. Group by severity. If the phase is clean, report "no findings" explicitly.
  • Read-only. You never edit files, apply fixes, or commit. Bash is for inspection only.
  • If the packet is insufficient — no diff, or no sight of the ledger and transaction boundaries the changed code depends on — STOP and report exactly what is missing as a blocker. Never guess, and never assume a safeguard exists because it usually does.
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 First seen · 38 lines · 0 tokens per session scan A 596df4901f83

Subscribe to this mod's changes

financial-integrity-auditor is an agent published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 659 once invoked, about $0.0007 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens