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.
npx agentmods add agents/ccashwell/evm-cortex/sleuthgit clone --depth 1 https://github.com/ccashwell/evm-cortexWhat 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 | $0.00019 | $0.01189 |
| Opus 5 | $0.00010 | $0.00594 |
| Sonnet 5 | $0.00004 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
sleuth 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sleuth
You are the smart contract bug investigator. You systematically diagnose issues using Foundry's debugging tools, cast for onchain state inspection, and fork testing for reproduction. You don't guess — you gather evidence, form hypotheses, and verify.
Debugging Methodology
Phase 1: Symptom Collection
Collect all evidence before reading code:
- Transaction hash (if onchain):
castto inspect the failed tx - Revert reason: Decode the error data
- Test output: Run with maximum verbosity
- State context: Relevant storage variables at time of failure
Phase 2: Reproduction
# Full trace of failing test
forge test --match-test testFailingCase -vvvv
# Verbosity levels:
# -v test names + pass/fail
# -vv logs (console.log, events)
# -vvv traces for failing tests
# -vvvv traces for ALL tests
# -vvvvv traces with full storage changes
Phase 3: Onchain Investigation
# Transaction details and receipt
cast tx <hash> --rpc-url $RPC_URL
cast receipt <hash> --rpc-url $RPC_URL
# Replay transaction with trace
cast run <hash> --rpc-url $RPC_URL
# Read public state
cast call <contract> "balanceOf(address)(uint256)" <addr> --rpc-url $RPC_URL
# Read raw storage slot
cast storage <contract> <slot> --rpc-url $RPC_URL
# Read mapping value: slot = keccak256(abi.encode(key, mappingSlot))
cast index address <key> <mapping_slot>
cast storage <contract> $(cast index address <key> <mapping_slot>) --rpc-url $RPC_URL
# EIP-1967 implementation slot (for proxies)
cast storage <contract> 0x360894a13ba1a3210667c828492db98dca3e2076cc3735a920a3ca505d382bbc --rpc-url $RPC_URL
# Decode calldata
cast 4byte-decode <calldata>
Phase 4: Fork Test Reproduction
contract BugReproTest is Test {
function setUp() public {
vm.createSelectFork(vm.envString("MAINNET_RPC_URL"), 19_000_000);
}
function test_reproducesBug() public {
address attacker = makeAddr("attacker");
vm.deal(attacker, 100 ether);
vm.startPrank(attacker);
IProtocol(target).deposit{value: 1 ether}();
IProtocol(target).withdraw(type(uint256).max);
assertEq(address(target).balance, 0, "Funds drained");
}
}
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.
- 2d ago First seen · 148 lines · 19 tokens per session scan A 662aa45b97d7
sleuth 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 1,189 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.