bounty-submit

bounty-submit is a command for coding agents from omermaksutii/RugProof. It costs 19 tokens per session (924 once invoked), scanned A, original, MIT.

A command that submits a confirmed security bug to a bug-bounty program such as Immunefi or Cantina. A bug bounty program pays researchers for eligible reports about security problems in participating projects.

In plain words
What is it for?
Use it to prepare and submit smart-contract vulnerability reports when the target program and platform are configured.
Why use it?
It prevents submitting an unverified issue and formats a confirmed finding for the correct program and severity. It requires a working proof-of-concept against a deployed contract that you do not own.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the rugproof plugin — 35 commands, 23 agents shipped together

Install

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.

agentmods
npx agentmods add commands/omermaksutii/rugproof/bounty-submit
Clone the repo
git clone --depth 1 https://github.com/omermaksutii/RugProof

Or install rugproof, the plugin that ships this one along with the rest of its 35 commands, 23 agents.

Wrote 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.

agentmods badge for bounty-submit

README.md
[![agentmods](https://agentmods.dev/badge/commands/omermaksutii/rugproof/bounty-submit.svg)](https://agentmods.dev/commands/omermaksutii/rugproof/bounty-submit)
Your own site
<a href="https://agentmods.dev/commands/omermaksutii/rugproof/bounty-submit"><img src="https://agentmods.dev/badge/commands/omermaksutii/rugproof/bounty-submit.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00924
Opus 5 $0.00010 $0.00462
Sonnet 5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00092

Measured 5d ago against content hash 23ec5fd95d50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bounty-submit scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://api.immunefi.com/v1/bug-reports \
commands/bounty-submit.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bounty-submit — submit to a bug bounty

Automates the submission of a confirmed finding to Immunefi (or another bounty platform). Strict prerequisites:

  • Finding must have a passing /exploit-live PoC against a deployed contract.
  • The contract must NOT be one you own (otherwise: just patch).
  • A bounty.yml config maps protocol-name → platform → program slug.

Procedure

1. Verify exploit reality

If the finding lacks a passing live PoC, refuse and tell the user to run /exploit-live first.

2. Resolve target program

# .rugproof.yml
bounty:
  immunefi:
    api_key: ${IMMUNEFI_API_KEY}
  cantina:
    api_key: ${CANTINA_API_KEY}
  default_platform: immunefi
  programs:
    - protocol: AcmeFi
      address: "0xabc..."
      platform: immunefi
      program_slug: acme-fi
      severity_map:
        Critical: critical
        High: high
        Medium: medium

If the chain+address has no entry, look up via the bounty platform's public directory.

3. Build the submission

Format it deterministically with the helper (maps severity to the program's scale, embeds the PoC, derives the program slug):

node "${CLAUDE_PLUGIN_ROOT}/scripts/dist/format-bounty.js" \
  --finding finding.json --program program.json \
  --poc test/live-exploits/Exploit.t.sol --out submission.json

It emits the Immunefi-style payload (submission.json) and, with no --out, the Markdown report on stdout. Sections it produces:

  1. Title[Critical] Reentrancy in Vault.withdraw drains funds
  2. Severity — translated per program's scale
  3. Affected asset — chain + address (proxy + impl if applicable)
  4. Bug description — clear, technical, no marketing
  5. Proof of concept — embed the passing Foundry test
  6. Reproduction steps — numbered
  7. Recommended mitigation — diff from /remediate
  8. Disclosure timeline — today as initial disclosure

4. POST to the platform

Immunefi:

curl -X POST https://api.immunefi.com/v1/bug-reports \
  -H "Authorization: Bearer $IMMUNEFI_API_KEY" \
  -H "content-type: application/json" \
  -d @submission.json

Read the full file on GitHub · 107 lines

Changes

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.

  1. 5d ago First seen · 107 lines · 19 tokens per session scan A 23ec5fd95d50

Subscribe to this mod's changes

bounty-submit is a command published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 924 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.