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/audit-changesgit 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-changes)<a href="https://agentmods.dev/commands/omermaksutii/rugproof/audit-changes"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/audit-changes.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 | $0.00018 | $0.00471 |
| Opus 5 | $0.00009 | $0.00235 |
| Sonnet 5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
audit-changes 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 3d 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-changes — audit only what changed
For PR review or pre-push verification. Audits only the diff vs $ARGUMENTS (default: main).
Procedure
- Get the diff.
git diff --name-only <base>...HEAD -- '*.sol' '*.vy'gives changed files. - For each changed file:
- Read the file and the diff hunk.
- Identify what changed: new function, modified function, new state var, etc.
- Audit the changes with extra attention to:
- Upgrade safety — did storage layout change? (use [[storage-layout]])
- New external-call sites — reentrancy review.
- New state mutations — access-control review.
- Changes to signed-message handling — replay review.
- Changes to oracle reads or price math.
- Removed
requires or relaxed checks.
- Cross-reference unchanged code. A diff that adds a new function to a contract requires understanding the existing invariants.
- Emit findings only for the diff — but flag pre-existing issues that the diff makes worse.
Output
Audit of diff vs <base>:
Files changed: N
Lines changed: +X / -Y
Findings: <severity breakdown>
Per finding, include the diff snippet and a recommended block-on-merge severity.
CI mode
When run from a hook (pre-push, pre-commit), this command:
- Reads
severity_thresholdfrom.rugproof.yml - Exits 0 if no findings at/above threshold
- Exits 1 with a structured stderr summary otherwise
Notes
- Don't re-audit code that didn't change.
- A new comment doesn't justify a finding — only changes to executable code.
- If the diff is huge, sample the most risky hunks (functions touching state, external calls, signatures) and tell the user the audit was sampled.
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.
- 3d ago First seen · 50 lines · 18 tokens per session scan A d4bfea11a3d6
audit-changes is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 471 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
phase6-start
Command "phase6-start" from kota1026/quantum-shield, covering phase 6 $arguments 開始, step 1: 進捗状況を確認, step 2: 未完了画面を特定, step 3: 必須ファイルを読み込む and step 4: インフラ確認.
codespace-verify
Command "codespace-verify" from kota1026/quantum-shield, covering codespaces ui確認コマンド, 1. codespaces起動確認, サービス起動状態確認, postgresql, redis, rabbitmqが起動していない場合 and フロントエンド起動.
pr-merge
Command "pr-merge" from kota1026/quantum-shield, covering pr作成・マージコマンド, 1. 変更確認, 2. コミット（未コミットがある場合）, 3. pr作成 and 4. マージ.
krait
Run a complete multi-phase security audit on the target codebase.
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
dashboard
Open the ChainGPT marketplace dashboard (localhost web UI — Overview, Skills, Activity, Health, About).