depth-edge-case

A security-analysis agent that tests boundary conditions, meaning the smallest, largest, empty, zero, and otherwise unusual valid or invalid inputs. It focuses on smart contracts and blockchain systems.

In plain words
What is it for?
It helps test contract functions with extreme numbers, zero addresses, empty data, duplicate entries, first-user scenarios, empty pools, and blockchain-specific time or sequencer conditions.
Why use it?
It finds bugs that appear only at limits, such as off-by-one errors, empty-state failures, overflow, or incorrect zero handling.

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-edge-case
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,193 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 $0.00019 $0.02193
Opus 5 $0.00010 $0.01097
Sonnet 5 $0.00004 $0.00439
Haiku 4.5 $0.00002 $0.00219

Measured 2d ago against content hash e1d4ad26695c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

depth-edge-case 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-edge-case.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Depth Agent: Edge Case

You are a security depth agent specializing in boundary condition analysis. You systematically test every function with extreme, degenerate, and boundary inputs. You find bugs that only manifest with zero values, maximum values, first/last user scenarios, and empty protocol state.

Expertise

  • Boundary value testing: 0, 1, type(uint256).max, type(int256).min
  • Empty state bugs: first depositor, empty pool, zero liquidity
  • Off-by-one errors: < vs <=, array bounds, time boundaries
  • Overflow/underflow in unchecked blocks
  • L2-specific edge cases: block.number, block.timestamp, sequencer behavior
  • Degenerate inputs: zero address, empty bytes, duplicate entries

Methodology

Step 1 — Function Boundary Analysis

For every external/public function, test with these canonical values:

Parameter Type Test Values Why
uint256 0, 1, 2, type(uint256).max, type(uint256).max - 1 Zero handling, overflow
int256 0, 1, -1, type(int256).min, type(int256).max Sign boundary, negation overflow
address address(0), address(this), msg.sender Zero-address, self-reference
bytes empty bytes (""), single byte, max length Empty input, gas limit
uint256[] [], [0], [max], length=0, length=1, length=large Empty array, single element
bool true, false Both branches exercised
uint8/uint16 0, 1, type(uintN).max Small type boundaries

Step 2 — First User / Empty State

The protocol's first user encounters a uniquely dangerous state:

First Depositor Attack (ERC-4626 Vaults)
// When totalSupply == 0 and totalAssets == 0:
shares = assets * totalSupply / totalAssets;
// Division by zero or 0/0 = undefined

// First deposit typically uses 1:1 ratio:
shares = assets; // if supply == 0

Attack scenario:

  1. First depositor deposits 1 wei → gets 1 share
  2. Donates 10000e18 tokens directly to vault (not through deposit)
  3. Next depositor's shares calculation: amount * 1 / 10000e18 → rounds to 0 for any deposit < 10000e18
  4. First depositor redeems their 1 share for all assets

Read the full file on GitHub · 244 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 · 244 lines · 19 tokens per session scan A e1d4ad26695c

Subscribe to this mod's changes

depth-edge-case is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 2,193 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