Quality

Daytona Recording Artifacts captures frame-by-frame HTML proof pages and optional MP4 videos from Daytona UI flows, so agents can include validated visual evidence in PRs and eval reports. Use it to document e2e workflows with named screenshots and a browseable index served from a persistent artifacts volume.

Daytona Windows Cert Test validates enterprise TLS and OS trust behavior on Windows inside a Daytona sandbox. Use it when testing a Windows build against corporate CA, GPO, or self-hosted certificate paths.

Fraimz creates a single fraimz.html proof artifact with one frame per step, binding claims, actions, assertions, voiceovers, and validated screenshots. Use it when a task ends with 'please create a fraimz' or when any change needs observable end-to-end proof.

iPolloWork Maintainable Code is a code-quality gate for AI agents editing application or server code, enforcing modern, minimal, performant, reuse-first implementation and clean repository ownership. It should be used whenever AI creates, edits, deletes, or refactors code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows.

Run Evals launches a real iPolloWork app on Daytona or local Electron and runs coded eval flows via CDP, producing machine-checkable assertions, screenshots, and reports used as PR evidence.

Bug Bounty guides a complete bug bounty workflow from reconnaissance and vulnerability hunting through validation and report writing, including LLM/AI security testing and A-to-B bug chaining. Use it for any bug bounty task, from starting a new target to writing the final submission.

Bug Bounty provides a complete bug bounty workflow covering reconnaissance, vulnerability hunting, AI/LLM security testing, bug chaining, and report writing. Use it for starting new targets, hunting specific vuln classes, auditing source code, validating findings, or writing reports.

Bug Bounty Methodology structures a hunting session around a five-phase workflow and a critical-thinking framework, so an agent can choose a goal, select techniques, and derive next actions. Use it at the start of a bug bounty session, when switching targets, or when unsure what to do next.

GraphQL Security Audit tests GraphQL endpoints for vulnerabilities such as introspection leaks, field suggestion abuse, batching DoS, IDOR via aliasing, auth bypasses, injection, subscription abuse, and depth bombs. Use it when a target exposes a GraphQL endpoint during security assessments.

Meme Coin Audit detects rug pulls in EVM and Solana token contracts, including honeypots, hidden mint, fee manipulation, LP drains, bonding curve exploits, and authority retention. Use it for pre-investment due diligence or token security reviews.

Mobile App Pentest tests Android/iOS apps by installing them, proxying traffic through Burp/mitmproxy, and driving the UI to capture API requests. It escalates to apktool/jadx and Frida/objection when traffic is pinned or absent to find hardcoded secrets and hidden endpoints.

Security Arsenal provides security payloads, bypass tables, wordlists, and bug bounty submission rules. Use it when testing for common web vulnerabilities or checking if a finding is submittable.