reentrancy

reentrancy is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 28 tokens per session (515 once invoked), scanned A, original, Apache-2.0.

A playbook for finding and validating reentrancy bugs in blockchain contracts. Reentrancy occurs when an external call lets another contract enter the original contract again before its state is safely updated.

In plain words
What is it for?
Use it to inspect external calls, trace call relationships, check protections such as ReentrancyGuard, and create Foundry tests that validate suspected attacks.
Why use it?
It helps uncover repeated withdrawals and less obvious attacks involving other functions, contracts, read-only calls, or token callbacks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect external calls, trace call relationships, check protections such as ReentrancyGuard, and create Foundry tests that validate suspected attacks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/reentrancy
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,491 stars · on GitHub · decepticon.red

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.

Any agent
npx skills add PurpleAILAB/Decepticon --skill reentrancy
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for reentrancy

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/reentrancy/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/reentrancy)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/reentrancy"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/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.

agentmods 80×15 button for reentrancy

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/reentrancy"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/reentrancy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00028 $0.00515
Opus 5 $0.00014 $0.00258
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 8d ago against content hash 991b96c87967, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

packages/decepticon/decepticon/skills/standard/contracts/reentrancy/SKILL.md · 53 lines

What it actually says

Reentrancy Playbook

Variants

  1. Classic — external call before state update (The DAO)
  2. Cross-function — A calls out, reentered into B which reads/writes A's state
  3. Read-only — view function reads stale state during reentrancy, consumed by a second contract making decisions
  4. Cross-contract — same attack pattern across protocol boundaries
  5. ERC777 / ERC1155 hookonERC*Received callback re-enters

Audit steps

  1. solidity_scan_file flags every .call{value:...} and delegatecall
  2. For each hit, check:
    • Is there a state write BEFORE the external call?
    • Is ReentrancyGuard's nonReentrant modifier applied?
    • Does it follow checks-effects-interactions?
  3. Trace call graph — if any function the call target can invoke reads or writes the same state slot, that's a reentrancy chain.

PoC via Foundry

foundry_reentrancy_test(target="Vault", function="withdraw", target_path="src/Vault.sol")

Then:

cp generated.t.sol /workspace/foundry/test/
cd /workspace/foundry && forge test -vvv --match-contract Test_withdraw

Success criteria

The attacker contract balance grows by more than its initial deposit after the attack transaction. The Foundry test should assert this.

CVSS

  • Direct fund drain: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H = 10.0
  • Read-only with downstream impact: 8.1-9.1 depending on impact

Known exemplars

  • The DAO (2016)
  • Lendf.Me (2020, ERC777 hook reentrancy, $25M)
  • Cream Finance (2021)
  • Rari Capital (2022)
  • Curve pool read-only reentrancy (2023)
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. 8d ago First seen · 53 lines · 28 tokens per session scan A 991b96c87967

Subscribe to this mod's changes

reentrancy is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 12d ago), licensed Apache-2.0. It adds 28 tokens to every session and 515 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 2026-09-03.