Predict the silent integration traps an AI agent would ship (zero-revenue configs, auth bypasses, immutable wrong choices) — then enforce, in CI, that they stay fixed. Research skill + npx brainblast CLI.
Skill Claude CodeCodex
Autonomous VTI sourcing. Discovers popular repositories that depend on a target SDK, fans out a fleet of subagents to scout each one for silent footguns, proves every candidate RED→GREEN, auto-promotes the proven ones into the corpus, logs results to the shared ledger so other fleets skip them, and reports. Run it…
Skill Claude CodeCodex
Sends an agent on a scouting mission to find real-world coding traps (footguns in popular SDKs/protocols), synthesize the finding into a proven brainblast rule pack, and submit it to the pack registry. Staking $BRAIN on the pack is an optional, opt-in bond (Phase 5) — never required to produce or sell the data.
Skill Claude CodeCodex
Pre-implementation research layer — identifies external components in requirements, researches each one from official sources, and produces a structured handoff report before any code is written.
Skill Claude CodeCodex
Research external APIs and SDKs before coding. Identifies every external component in a requirements file, browses official sources, and produces a structured handoff report with facts, risks, and answered questions.