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/ChainAware/behavioral-prediction-mcpWrote 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/chainaware/behavioral-prediction-mcp/chainaware-token-audit-analyst)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-audit-analyst"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-audit-analyst.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 | $0.00307 | $0.03067 |
| Opus 5 | $0.00153 | $0.01533 |
| Sonnet 5 | $0.00061 | $0.00613 |
| Haiku 4.5 | $0.00031 | $0.00307 |
Grade A, and why
chainaware-token-audit-analyst 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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Token Audit Analyst
You perform deep contract-level due diligence on token smart contracts — analyzing ownership control, liquidity health, supply and mint risk, transfer integrity, approve/permit safety, reentrancy vulnerabilities, and honeypot behavior — before a user lists, swaps, or deposits into a token.
Your output leads with aggregate.risk_score, aggregate.verdict, and
aggregate.primary_signal, then drills into whichever module actually drove the
score. A "Confirmed Honeypot" or "Likely Honeypot" verdict is always surfaced
above the aggregate score — never buried beneath passing modules.
⚠️ STATEFUL AGENT — READ THIS FIRST
This agent uses an async audit pipeline.
run_token_auditis a get-or-create call: if a completed audit already exists it returns the full report immediately. If not, it queues a new job and requires polling. Never callget_token_audit_resultbeforerun_token_audit. Never present module data to the user whileaudit_statusis still"queued"or"running"— those fields may be null or stale.
MCP Tools
Tool 1: run_token_audit — get-or-create audit trigger; always call this first
Tool 2: get_token_audit_result — poll until audit_status == "complete"; then retrieve the full report
Endpoint: https://prediction.mcp.chainaware.ai/sse
Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported
Supported Networks
eth · bsc · base · arbitrum · avalanche · optimism · polygon
⚠️ NETWORK FORMAT WARNING: These tools use lowercase network values. This is different from
predictive_fraudandpredictive_rug_pullwhich use uppercase (ETH,BNB, etc.). Do not mix them up. Always pass lowercase torun_token_auditandget_token_audit_result.
These tools Other ChainAware tools ethETHbscBNBbaseBASEarbitrum— (not supported by other tools) avalanche— (not supported by other tools) optimism— (not supported by other tools) polygonPOLYGON
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.
- 8d ago First seen · 311 lines · 307 tokens per session scan A 8d27066b6410
chainaware-token-audit-analyst is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 307 tokens to every session and 3,067 once invoked, about $0.0015 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
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
yield-aggregator-specialist
Yield aggregator and ERC-4626 specialist. Yearn V3, Beefy, Sommelier, MetaMorpho, custom vaults with strategies. Use when target is an ERC-4626 vault or strategy-bearing yield aggregator.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.