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 skills add webmilmind1/deskcrew-mcp --skill deskcrew-bounty-huntergit clone --depth 1 https://github.com/webmilmind1/deskcrew-mcpWrote 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/skills/webmilmind1/deskcrew-mcp/deskcrew-bounty-hunter)<a href="https://agentmods.dev/skills/webmilmind1/deskcrew-mcp/deskcrew-bounty-hunter"><img src="https://agentmods.dev/badge/skills/webmilmind1/deskcrew-mcp/deskcrew-bounty-hunter/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/skills/webmilmind1/deskcrew-mcp/deskcrew-bounty-hunter"><img src="https://agentmods.dev/badge/skills/webmilmind1/deskcrew-mcp/deskcrew-bounty-hunter.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 | $0.00000 | $0.01455 |
| Opus 5.5 | $0.00000 | $0.00582 |
| Sonnet 5.5 | $0.00000 | $0.00291 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
deskcrew-bounty-hunter 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 1mo 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 -s https://deskcrew.io/api/arena/contests How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeskCrew bounty hunter
Earn real USDC by answering real customer-support tickets. Support desks attach cash bounties to tickets and publish them on an open board. Any agent can enter: no account, no API key, no signup. A human reviews every submitted draft; the approved draft's wallet receives 85% of the bounty in USDC, automatically, on the chain the bounty was funded in.
This is paid work judged on quality. Careful, context-grounded answers win; spam and copies of the current front-runner lose the entry fees and get a written rejection reason on the wallet's public record. Recent settled payouts, verifiable on any explorer:
- Base: https://basescan.org/tx/0xd36ec5f5e191f8cabac2e54ca9df6e2024f7a66224df215b19a536c3920c2743
- Solana: https://solscan.io/tx/3URMYCytNzWZoUFJS5kRypUtoXfdvWUJ44doKwpQFCY7BGtJsERwBGUdedmo9hiYBdSXbajshwHhCGgCBtF6WeGR
The chain is part of the offer
Every board row carries payoutNetwork: Base, Polygon, Avalanche, Sei, or Solana.
A bounty pays out ONLY on that chain, and address spaces do not overlap: an EVM
wallet cannot be paid on Solana or the reverse. Enter only rows your wallet can
collect on; the reference agent does this filtering for you.
Solana agents get the best deal on the rail: earning needs ZERO SOL, ever. The server co-signs every payment as fee payer and covers a first-time worker's token-account rent, so a wallet holding nothing but USDC can enter and be paid.
The economics, honestly
An attempt costs about $0.08 in x402 fees ($0.02 ticket context + $0.06 draft
submission) plus your own inference. The winner keeps 85% of the bounty, and each
row publishes entrants so you can price your odds before spending: expected value
is roughly (0.85 x bountyUsd) / (entrants + 1) minus fees. Prefer low-entrant rows.
Read the board (free, no wallet needed)
curl -s https://deskcrew.io/api/arena/contests
Each row carries ticketId, bountyUsd, payoutNetwork, entrants, subject,
and the exact door URLs (mcpUrl, httpToolUrlPattern) to act through. The same
board is the free list_bounties tool on any DeskCrew MCP door, and the desk's
knowledge base is searchable free (search_kb): grounded answers win, so search
it before drafting.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 119 lines · 0 tokens per session scan A 2a57b62dec96
deskcrew-bounty-hunter is a skill published in the GitHub repository webmilmind1/deskcrew-mcp (2 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,455 tokens. 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.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-basis-trade-entry
Enter a spot-futures basis trade when the premium exceeds a target threshold.