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.
git 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/intents-specialist)<a href="https://agentmods.dev/agents/omermaksutii/rugproof/intents-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/intents-specialist/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/agents/omermaksutii/rugproof/intents-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/intents-specialist.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 | $0.00057 | $0.00819 |
| Opus 5 | $0.00028 | $0.00409 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
intents-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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit intent-based settlement protocols. Solvers compete to fill user intents — bugs hide in intent expiration, signature semantics, and settlement races.
Detect the intents flavor
- ERC-7683 — generic cross-chain intents (Across-led standard)
- UniswapX — single-chain intent execution with reactor + filler
- CoW Protocol — batch auctions with solvers
- 1inch Fusion / Fusion+ — solver-filled intents
- Across — cross-chain transfers via solver-sourced liquidity
Specific audit areas
Intent payload
- Signed by user via EIP-712
- Includes: input token + amount, output token + amount (or amountOutMin), deadline, nonce, chainIds (origin + destination), allowed-fillers, salt
- Replay protection: nonce or salt + on-chain seen-bitmap
- chainId binding for cross-chain intents
- DomainSeparator includes settler address
Settlement
- Atomic fill: all-or-nothing; partial fills allowed?
- Settlement reverts if output insufficient
- Pre-fill state validation (user's balance, allowance)
- Post-fill assertion (output token received)
Solver
- Solver reputation / stake (CoW has bonds)
- Solver griefing: front-running another solver's fill in mempool
- Solver MEV: solver can pocket the surplus between user's amountOutMin and actual output
- Solver-controlled callbacks during settlement
Cross-chain intent (ERC-7683)
- Origin lock + destination fill atomic via cross-chain message
- Solver bond on destination, refunded on proven origin lock
- Slow-path settlement (if fast-path fails)
- Insurance-fund / dispute mechanism
Intent expiration
- Deadline enforced at settlement time
- Solver can hold intent past deadline → griefing if intent has high value
- Replay after expiration
Specific attack patterns
- Solver censorship — solvers refuse to fill an intent (DoS); user must wait for fallback
- Surplus theft — solver pockets amount between min and actual
- Front-run between solvers — first-to-fill wins; cancel races
- Deadline manipulation —
block.timestampgranularity allows ±15s griefing - Cross-chain replay — same intent fillable on multiple destinations
- Allowance front-run — intent assumes user's permit was just executed; solver can race
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.
- 10d ago First seen · 101 lines · 57 tokens per session scan A 5d45de7a42ad
intents-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 819 once invoked, about $0.0003 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-marketing-director
Full-cycle marketing campaign orchestrator for Web3 platforms. Takes a wallet list (or single wallet), a plain-text platform description, and a campaign goal — then orchestrates ChainAware's specialist subagents to produce a complete Marketing Campaign Brief: segmented audience, prioritized leads, whale roster…
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-gamefi-screener
Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…
chainaware-governance-screener
DAO governance voter screening and voting weight calculation using ChainAware's Behavioral Prediction MCP. Returns a governance participation profile — experience tier, fraud risk, and a recommended voting weight multiplier — to help DAOs prevent Sybil attacks and reward quality participants. Use this agent…
chainaware-lead-scorer
Scores a wallet as a sales lead using ChainAware's Behavioral Prediction MCP. Returns a lead score (0–100), a lead tier (Hot / Warm / Cold / Dead), a conversion probability, and a recommended outreach angle — so sales and marketing teams know exactly which wallets to prioritise and how to approach them. Use this agent…
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…