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/bountygit 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/bounty)<a href="https://agentmods.dev/commands/omermaksutii/rugproof/bounty"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/bounty.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 | $0.00024 | $0.00651 |
| Opus 5 | $0.00012 | $0.00326 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
bounty 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 4d 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.
/bounty — generate a bounty submission
After you find a real bug in a deployed contract, this command prepares a responsible-disclosure submission.
Procedure
Step 1 — Confirm the finding is real
Require the finding ID to have a passing /exploit-live proof on a fork. Otherwise, refuse to generate (no theoretical disclosures).
Step 2 — Pick the target
immunefi— uses Immunefi's submission formatprotocol— uses the protocol's documented bounty form (auto-detect from chain + address)seal911— SEAL 911 (emergency, for actively exploitable critical vulns)
Step 3 — Generate the submission
Sections required by most bounty programs:
- Title (one-line, severity-loaded)
- Severity (per the protocol's bounty scale — usually Critical/High/Medium)
- Impact summary (who can lose what, how much, how fast)
- Affected contracts (addresses, on which chain)
- Bug description (clear, technical, no marketing)
- Reproduction steps (step-by-step)
- Working PoC (paste the Foundry test from
/exploit-live) - Recommended mitigation (the patch from
/remediate) - Disclosure timeline (today's date as initial disclosure)
Step 4 — Sensitive-data warnings
Before output, scan for:
- Hardcoded private keys, mnemonics
- Personal info
- Internal-only URLs
If found, refuse to write to disk; warn the user.
Step 5 — Output
Write to rugproof-reports/bounty-<finding-id>-<date>.md. Tell the user:
✓ Bounty submission generated: rugproof-reports/bounty-REENT-001-2026-05-12.md
Target: Immunefi
Project: Acme Protocol (acme.fi)
Severity: Critical
Estimated payout (per program): $50K - $250K
Next steps:
1. Review the submission for accuracy
2. Submit at https://immunefi.com/bounty/acme/
3. DO NOT share the PoC publicly until the protocol acknowledges
If actively exploitable in the wild RIGHT NOW:
→ Contact SEAL 911: https://seal-911.com (emergency channel)
Notes
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.
- 4d ago First seen · 73 lines · 24 tokens per session scan A b86cc51a38fa
bounty is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 651 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.
fix-btc-e2e-p11
Fix errors in BTC E2E test (Pattern 11: P2TR Tapscript M-of-N).
fix-btc-e2e-p2
Fix errors in BTC E2E test (Pattern 2: P2PKH 2-of-3 Multisig).