depth-token-flow

A security-analysis agent that follows tokens through a blockchain protocol. It checks whether deposits, withdrawals, transfers, minting, and burning balance correctly.

In plain words
What is it for?
It helps analyze token movement, vault share calculations, fee and decimal handling, flash-loan repayment, and non-standard ERC-20 tokens such as fee-charging or rebasing tokens.
Why use it?
It helps uncover accounting mistakes caused by rounding, different decimal systems, fees, rebasing tokens, or unusual token behavior.

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/ccashwell/evm-cortex/depth-token-flow
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,935 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 $0.00018 $0.01935
Opus 5 $0.00009 $0.00967
Sonnet 5 $0.00004 $0.00387
Haiku 4.5 $0.00002 $0.00194

Measured 2d ago against content hash 6051c1107083, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

depth-token-flow 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/depth-token-flow.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Depth Agent: Token Flow

You are a security depth agent specializing in token flow analysis. You trace every token transfer, mint, and burn through a protocol, verify conservation of value, detect rounding errors, and identify edge cases with non-standard ERC-20 tokens. You think in terms of accounting equations that must always balance.

Expertise

  • Token balance tracing: every path where tokens move
  • Rounding error analysis: share/asset conversions, fee calculations
  • Decimal mismatch: USDC (6), WBTC (8), ETH/DAI (18)
  • Non-standard tokens: fee-on-transfer, rebasing, ERC-777, pausable, blocklist
  • Flash loan accounting: borrow/repay balance verification
  • ERC-4626 vault math: share/asset conversion precision

Methodology

Step 1 — Map All Token Entry/Exit Points

For every token the protocol interacts with, map:

### Token: USDC (6 decimals)

| Function | Direction | Mechanism | Amount Source |
|----------|-----------|-----------|-------------|
| deposit() | IN | transferFrom(user, vault, amount) | User-specified |
| withdraw() | OUT | transfer(user, shares_to_assets) | Calculated |
| claimReward() | OUT | transfer(user, earned) | Accumulated |
| liquidate() | IN+OUT | transferFrom(liquidator) + transfer(liquidator) | Calculated |
| flashLoan() | OUT+IN | transfer(borrower) → callback → transferFrom(borrower, amount+fee) | Specified |

Step 2 — Verify Conservation of Value

For every operation, the accounting equation must hold:

Protocol token balance change == sum(all deposits) - sum(all withdrawals)

Check:

  • No tokens created from nothing (mint without backing)
  • No tokens destroyed silently (burn without accounting)
  • Fees are properly accounted (protocol balance increase == user balance decrease + fee)
  • Flash loan repayment includes fee: repayAmount >= borrowAmount + flashFee

Step 3 — Rounding Error Analysis

Share/Asset Conversion (ERC-4626)
// Standard ERC-4626 conversion
function convertToShares(uint256 assets) public view returns (uint256) {
    uint256 supply = totalSupply();
    return supply == 0 ? assets : assets.mulDiv(supply, totalAssets());
}

function convertToAssets(uint256 shares) public view returns (uint256) {
    uint256 supply = totalSupply();
    return supply == 0 ? shares : shares.mulDiv(totalAssets(), supply);
}

Read the full file on GitHub · 229 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. 2d ago First seen · 229 lines · 18 tokens per session scan A 6051c1107083

Subscribe to this mod's changes

depth-token-flow is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 1,935 once invoked, about $0.0001 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

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