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 skills add UnboundCompute/security-agent-skills --skill hunting-smart-contract-reentrancygit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/skills/unboundcompute/security-agent-skills/hunting-smart-contract-reentrancy)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-smart-contract-reentrancy"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-smart-contract-reentrancy/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/skills/unboundcompute/security-agent-skills/hunting-smart-contract-reentrancy"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-smart-contract-reentrancy.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 | $0.00190 | $0.01948 |
| Opus 5.5 | $0.00076 | $0.00779 |
| Sonnet 5.5 | $0.00038 | $0.00390 |
| Haiku 4.5 | $0.00019 | $0.00195 |
Grade A, and why
hunting-smart-contract-reentrancy 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting smart-contract reentrancy: acting on state that has not been updated yet
Reentrancy is a control-flow bug: a contract makes an external call before it finishes updating its own state, and the callee, which the attacker controls, calls back in and finds the old state still in place. The classic shape is sending value before zeroing a balance, but it generalizes to any effect that lands after an interaction, across functions that share state and through callback hooks that hand the attacker control mid-update. This is a crowded topic, so the value is not naming the pattern but killing the lead that a guard or an already-updated state defeats. The dividing line from access control: if the fix is to reorder effects before interactions or add a mutex, it is reentrancy and belongs here; if the fix is to add or repair an authorization check, it belongs in the access-control skill.
When to use
- A function makes an external call (sends value, calls a token, invokes an attacker-supplyable address).
- State that the function or a sibling depends on is updated after that external call.
- You want to know whether an attacker can re-enter and act on state that has not been updated yet.
Scope check
Analyze only contracts you own or are authorized to assess, and exercise a reentrancy path only on a test network or a local fork, never against live value, an exploit here moves real funds irreversibly. Prove it against a fork. If you can't name the authorization, stop.
The loop
-
Map external calls against state updates first. For each function, find every external call (a value transfer, a token call, a call to a supplied address) and every state update the function and its siblings depend on, and record which comes first. Reentrancy exists only where an effect lands after an interaction; establish that ordering before anything else.
-
Check single-function reentrancy. Look for a function that performs an external call before updating the state that call's safety depends on, the withdraw-before-zeroing shape, so a re-entrant call sees the pre-update balance and repeats the withdrawal.
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.
- 1mo ago First seen · 127 lines · 190 tokens per session scan A ee8098ec5953
hunting-smart-contract-reentrancy is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 1,948 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.