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/commands/omermaksutii/rugproof/audit-history)<a href="https://agentmods.dev/commands/omermaksutii/rugproof/audit-history"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/audit-history/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/commands/omermaksutii/rugproof/audit-history"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/audit-history.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 | $0.00025 | $0.00566 |
| Opus 5 | $0.00013 | $0.00283 |
| Sonnet 5 | $0.00005 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
audit-history 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 9d 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.
What it actually says
/audit-history — what's been found before
For $ARGUMENTS (an address or protocol name), retrieve historical audit findings.
Procedure
- Resolve target. If
$ARGUMENTSis an address, useblock-explorerto get the contract name and protocol attribution. If it's a name, query both history MCPs directly. - Query both history MCPs in parallel.
mcp__c4-history__search(protocol=<name>) mcp__sherlock-history__search(protocol=<name>) - Aggregate. Deduplicate findings across sources. Group by:
- Severity (Critical → Info)
- Vuln class (mapped to a [[skills]] category)
- Date
- Cross-reference current code. If we have current source (via
block-exploreror local repo):- For each historical finding, check whether the affected pattern is still present.
- Flag findings where the fix is unclear in the current code.
Output
Historical findings for <protocol>:
Audited by: Code4rena (2024-06), Sherlock (2024-09), Spearbit (2024-12)
Total public findings: N (C: x, H: y, M: z, L: w, I: v)
Top critical:
[C4-2024-06 #042] Cross-function reentrancy in withdraw()
Pattern: reentrancy (cross-function)
Status: ✅ fixed in commit 0xabc...
[Sherlock-2024-09 #007] Read-only reentrancy on getReserves
Pattern: reentrancy (read-only)
Status: ⚠ similar pattern still present at Vault.sol:142
Carry-over risks (still applicable):
[...]
Why this is useful
- New auditors can avoid duplicating prior work.
- Pattern recurrence is a strong signal that the team may have missed the lesson.
- Useful pre-audit context: "what did the last firm find?"
Notes
- C4 / Sherlock histories are public but rate-limited; cache results via the MCP.
- For protocols audited by private firms (Trail of Bits, OpenZeppelin), public findings may not exist — report "no public history" rather than fabricating.
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.
- 9d ago First seen · 57 lines · 25 tokens per session scan A 6f9f9e10624b
audit-history is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 566 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 2026-08-31.
Other commands, from other repositories
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
verify-e2e-flow
Verify that the E2E scripts for the specified chain follow the documented transaction flow.
keygen-wallet
Keygen Wallet operates offline as a cold wallet. It generates keys, creates multisig addresses, and provides the first signature for multisig transactions.
watch-wallet
Watch Wallet operates online and manages public keys only. It creates unsigned transactions, sends signed transactions, and monitors transaction status.
fix-btc-e2e-p11
Fix errors in BTC E2E test (Pattern 11: P2TR Tapscript M-of-N).