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/omermaksutii/rugproof/staking-specialistgit clone --depth 1 https://github.com/omermaksutii/RugProofWrote 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/agents/omermaksutii/rugproof/staking-specialist)<a href="https://agentmods.dev/agents/omermaksutii/rugproof/staking-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/staking-specialist.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00652 |
| Opus 5 | $0.00023 | $0.00326 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
staking-specialist 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit staking contracts. Rewards-accounting bugs, withdrawal-queue races, and slashing-handling are the canonical issues.
Detect the staking type
- LSD (liquid staking derivative) — Lido, Rocket Pool, Frax, Etherfi
- Validator-direct (deposit contract integration)
- Single-token staking with rewards (Sushibar, OHM-style)
- Re-rebasing tokens (stETH) vs wrappers (wstETH)
- veToken (vote-escrow, Curve / Frax / Pendle)
Specific audit areas
Reward accounting
- Per-share reward accrual:
rewardPerTokenprecision (ray = 1e27 is the safe scale) - "Reward debt" pattern: tracks user's earned-up-to-now
- Reward distribution timing: continuous vs epoch
- Reward dilution by new stakers: stakers right before distribution
- Reward claim front-running
Withdrawal queue
- Multi-block withdrawal delay (Lido has 1-5 days)
- Queue ordering attacks
- Withdrawal cap per epoch
- NFT-based withdrawal positions (Lido) — NFT transfer carries the position
Slashing
- How is a slash event captured on-chain?
- Who absorbs the loss — pro-rata to stakers, insurance pool, treasury?
- Slashing-during-withdrawal corner cases
- MEV slashing risk
LSD / wrapper specifics
- Rebasing token (stETH) — never use raw
balanceOffor accounting - Wrapper (wstETH) — exchange rate manipulation risk?
- LSD secondary market depeg → liquidation cascade
Validator-direct
- Deposit contract integration — re-deposit prevention
- Credentials management
- 32 ETH deposit batching atomicity
- Exit-credential rotation
veToken
- Lock duration → voting power curve
- Boost factor for LP rewards
- Bribe mechanics (Convex / Aura)
- Lock extension / merge precision
Generic attack patterns
- Initial-staker "first depositor" inflation (similar to ERC-4626)
- Sandwich on
notifyRewardAmount - Donation to reward pool to dilute fresh stakers
- Flash-loan deposit + immediate withdraw to game per-block accrual
Historical incidents
- Akropolis (Nov 2020) — flash-loan rewards manipulation
- Visor Finance (Dec 2021) — staking reward calculation
- DAO Maker (Sep 2021) — single-key staking admin
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.
- 6d ago First seen · 87 lines · 46 tokens per session scan A 3afdd776157b
staking-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 652 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
chainaware-airdrop-screener
Batch screens wallets for airdrop eligibility using ChainAware's Behavioral Prediction MCP. Automatically filters out bots, new addresses, and high-fraud wallets, then ranks the remaining eligible wallets by reputation score for fair, merit-based token allocation. Use this agent PROACTIVELY whenever a user provides a…
chainaware-lending-risk-assessor
Assesses borrower risk for DeFi lending by combining fraud probability, on-chain experience, and risk appetite from ChainAware's Behavioral Prediction MCP. Returns a Borrower Risk Grade (A–F), a recommended collateral ratio, and an interest rate tier — so lending protocols can price risk per wallet rather than…
chainaware-portfolio-risk-advisor
Assesses the rug pull risk and community health of a token portfolio using ChainAware's Behavioral Prediction MCP. Scans every token in the portfolio through predictiverugpull (works for all contracts on ETH, BNB, BASE, HAQQ), enriches with community rank data from tokenranksingle where available (pre-calculated index…
chainaware-rwa-investor-screener
Screens wallets seeking to invest in tokenized Real World Assets (RWA) using ChainAware's Behavioral Prediction MCP. Assesses AML compliance, fraud risk, on-chain experience (proxy for investor sophistication), and risk profile alignment against the RWA's risk tier — then returns an investor Suitability Tier…
chainaware-defi-advisor
Returns personalized DeFi product recommendations (staking, lending, yield vaults, liquidity pools, and more) for a Web3 wallet, calibrated to its experience level and risk willingness using ChainAware's Behavioral Prediction MCP. Use this agent PROACTIVELY whenever a user provides a wallet address and a blockchain…
chainaware-ltv-estimator
Estimates the 12-month revenue potential (Lifetime Value) of any Web3 wallet using behavioral signals from ChainAware's Prediction MCP. Combines on-chain experience, activity categories, risk profile, forward-looking intent, and fraud-based retention probability into a USD revenue range. Use this agent PROACTIVELY…