Bounty Operator llms.txt changelog

https://bountyoperator.com/llms.txt

− > Pre-submission review for bug bounty reports and smart-contract findings. The AI argues against the finding. The hunter writes the report. Reviews run on the user's own AI provider API key. Free: 1 review a day. Operator: US$10 per month for unlimited reviews and US$2 API credit per paid month. Only hosted reviews count: on the site or through `run_review`.+ > Make your strongest case before you submit. Check your proof, make the impact explicit, and catch missing evidence before the triager has to ask.+ Pre-submission review for bug bounty reports and smart-contract findings. The review checks claims and counterarguments against the supplied evidence, confirms supported claims and identifies gaps. The hunter writes the report. Start with the free core workflow: `list_profiles`, `prepare_review`, your own model's review, then `build_packet`. It needs no Bounty Operator account or provider key. Hosted reviews through `run_review` are separate: Free allows 1 a day on the user's API key; Operator i+ - [Novita BYOK setup](https://bountyoperator.com/docs/model-selection#novita): Optional hosted-review provider `novita`; local MCP key variable `NOVITA_API_KEY`. In the remote MCP endpoint use `provider: "novita"` and send the key in `X-Provider-Key`, never a tool argument. Website selection: https://bountyoperator.com/?provider=novita#workspace. Check Novita's current pricing, credit and data policies; it bills model usage separately. Bounty Operator account and hosted-review allowances still a+ - [Nebius BYOK setup](https://bountyoperator.com/docs/model-selection#nebius): Optional hosted-review provider `nebius` (Nebius Token Factory); local MCP key variable `NEBIUS_API_KEY`. In the remote MCP endpoint use `provider: "nebius"` and send the key in `X-Provider-Key`, never a tool argument. Website selection: https://bountyoperator.com/?provider=nebius#workspace. Default model `deepseek-ai/DeepSeek-V4.1-Flash`. Requests send `store: false`. Nebius bills model usage separately; Bounty Opera+ - OpenCode v1: merge `{"mcp":{"bounty-operator":{"type":"remote","url":"https://bountyoperator.com/api/mcp","oauth":false}}}` into the project's `opencode.json`. OpenCode v2: put the same server entry under `mcp.servers`, not directly under `mcp`. Verify with `opencode mcp list`. Versioned local and hosted configs: https://bountyoperator.com/mcp#install+ - First call: use `list_profiles`, then `prepare_review` for `general`, `solidity` or `report` with only the files the user chose. The remote endpoint needs `files` with inline text, not local `paths`. Respect privacy blocks, write the review from the prepared request, then pass the unchanged manifest and review to `build_packet`. Report reference problems instead of presenting the packet as verified proof.+ - Free-model options and data-use limits: https://bountyoperator.com/docs/model-selection#free. The website can check OpenRouter's current zero-priced models; a free provider model does not bypass Bounty Operator's hosted-review allowance or prove review quality. Never silently switch a free request to a paid model.

https://bountyoperator.com/llms.txt

− > Pre-submission review for bug bounty reports and smart-contract findings. The AI argues against the finding. The hunter writes the report. Reviews run on the user's own model key. Free: 1 review a day. Operator: US$10 per week for unlimited reviews. Only hosted reviews count: on the site or through `run_review`.− - [Workbench](https://bountyoperator.com/#workspace): Select files, pick a review profile and run it on your own model key. The three core profiles also export as a prompt.− - [Pricing](https://bountyoperator.com/pricing): Free gives you 1 review a day, any review type (reset at 00:00 UTC). Operator is US$10 per week for unlimited reviews, the Gauntlet, Panel review and 4 reviews at once. The review of the day is a hosted review, on the site or through `run_review`. Copy-paste reviews in a chat app, and core reviews the agent's own model writes through `prepare_review` or the skills, need no account and are not counted.− - [Report templates](https://bountyoperator.com/templates): Templates for four platforms and a Foundry PoC scaffold.− - [Immunefi](https://bountyoperator.com/templates/immunefi): Immunefi bug report template in Markdown.− - [Terms of service](https://bountyoperator.com/terms): Plans, the weekly renewal, cancellation, refunds and the rules of use.+ > Pre-submission review for bug bounty reports and smart-contract findings. The AI argues against the finding. The hunter writes the report. Reviews run on the user's own AI provider API key. Free: 1 review a day. Operator: US$10 per month for unlimited reviews and US$2 API credit per paid month. Only hosted reviews count: on the site or through `run_review`.+ - [Model API](https://bountyoperator.com/model-api): Hosted cybersecurity and low-refusal model API (`/v1/chat/completions`, `/v1/models`) with prepaid credit, per-key spending limits, function tools, streaming, workload cost estimator and interactive quickstart, plus native Infron 7-model cybersecurity stack support (`provider: "infron"`, `INFRON_API_KEY`) in the workbench, Gauntlet, Panel review, CLI and MCP. No subscription required; the monthly Operator plan includes US$2 API credit per paid+ - [Workbench](https://bountyoperator.com/#workspace): Select files, pick a review profile and run it on your own AI provider API key. The three core profiles also export as a prompt.+ - [Pricing](https://bountyoperator.com/pricing): Free gives you 1 review a day, any review type (reset at 00:00 UTC). Operator is US$10 per month for unlimited reviews, the Gauntlet, Panel review and 4 reviews at once. Includes US$2 in Bounty Operator API credit per paid month; other providers bill usage separately. Existing weekly subscriptions keep their Stripe billing interval and do not receive the monthly credit. The review of the day is a hosted review, on the site or through `run_review`.+ - [Report templates](https://bountyoperator.com/templates): Templates for four platforms, GitHub private vulnerability reports and a Foundry PoC scaffold.+ - [Immunefi](https://bountyoperator.com/templates/immunefi): Immunefi bug report template in Markdown, for bug bounties and audit competitions, with the per-report fee.+ - [GitHub private vulnerability report](https://bountyoperator.com/templates/github-private-vulnerability-report): Template for the structured form GitHub uses since 1 Oct 2026: summary, details, proof of concept, impact.+ - [Model API setup guide](https://bountyoperator.com/docs/model-api): Connect agents and chat tools, discover models, send requests and understand prepaid billing.+ - [Choose a model](https://bountyoperator.com/docs/model-selection): Compare workflow needs, capabilities, cost, availability, data handling and evaluation evidence.+ - [Terms of service](https://bountyoperator.com/terms): Plans, monthly renewal, legacy weekly subscriptions, API credit, optional auto top-ups, cancellation, refunds and the rules of use.