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 commands/omermaksutii/rugproof/gasgit 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/gas)<a href="https://agentmods.dev/commands/omermaksutii/rugproof/gas"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/gas.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 | $0.00016 | $0.00630 |
| Opus 5 | $0.00008 | $0.00315 |
| Sonnet 5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
gas 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 5d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gas — gas profile and optimization
Procedure
Step 1 — Run forge gas report
mcp__forge-runner__gas_report()
Returns per-function gas costs from the existing test suite.
Step 2 — Identify expensive ops
Dispatch gas-optimizer subagent. It looks for:
- Storage reads in loops — should be cached in memory
- SSTORE on cold slots that could be merged into one slot (packing)
- String revert reasons — use custom errors (
error InsufficientBalance();) - Unbounded loops over storage
x = x + 1instead of++x/unchecked { ++x }in safe loops- Memory vs calldata for read-only function params (calldata is cheaper)
- Public vs external for fns called only externally (external is cheaper)
- Repeated keccak256 of constants — precompute
requireover short-circuit when both sides are equally cheap- Bool storage flags — pack into bitfields if grouped
- Modifier with body inlined vs reusable — inline can be cheaper
Step 3 — Generate suggestions
For each opportunity, produce a diff. Estimate gas saved using a benchmark test.
Step 4 — Apply and measure
If --apply, apply the patches and re-run gas report. Show before/after.
Step 5 — Output
Gas profile for src/Vault.sol:
Function Avg Min Max Median
deposit 147K 142K 158K 144K
withdraw 203K 189K 225K 198K ← top spender
rebalance 412K 398K 431K 410K ← top spender
Optimization opportunities:
1. withdraw():
- Cache `users[msg.sender]` in memory (called 4× in fn body)
- Estimated savings: 8K gas/call
2. rebalance():
- Replace `string memory reason` with custom errors
- Estimated savings: 12K gas/call
3. Storage layout:
- Pack `bool paused` + `uint8 feeRate` + `address admin` into one slot
- Saves one SSTORE per init: 20K gas
Apply with --apply. Re-runs the gas report and shows deltas.
Notes
- Don't sacrifice readability for marginal gas wins.
- Avoid assembly optimizations unless gas savings are >10K and the code is well-commented.
- Re-audit any gas-optimized code — assembly substitutions are a common bug source.
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.
- 5d ago First seen · 73 lines · 16 tokens per session scan A 5e81a63cdda2
gas is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 630 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.
krait-quick
Run a streamlined audit: Recon → Detection → Verification → Report. Skips state inconsistency analysis and cross-feed iteration for speed.
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.