food-chain-code

Food Chain Code

Adversarial architecture stress-tester. Each agent attacks a technical decision from a distinct failure vector under strict role-lock. Weak arguments are eliminated each round. Survivors absorb and evolve. The architecture patches itself. One apex predator remains — and the design that survived it is the design worth building.

---

What This Is

The only adversarial skill built for software architecture decisions, not product validation. It produces structural insights a single-pass review cannot — because each attacker operates in isolation, the elimination mechanic forces genuine technical pressure, and the architecture is stress-tested against its evolved version in every subsequent round. Use it before writing code, not after.

What This Is Not

• A code review tool. This attacks architecture decisions, not implementations.
• A brainstorming tool. The architecture must already be proposed. Use a design skill first if not.
• A product validation tool. For product ideas, use food-chain-ideation.
• A benchmarking tool. It does not measure performance — it predicts structural failure.
• A linter or static analysis replacement. Those catch bugs. This catches regret.

---

Prerequisites

Read references/code-animal-library.md before designing any ecosystem. Use the Quick Selection Guide at the top of that file to identify candidate animals fast. Never invent behavioral traits from scratch. Never select animals whose failure vectors overlap. Check the Anti-Pattern Combinations section before finalizing the ecosystem.

---

Pre-Flight Checks

Run these before starting the battle. If any fail, fix them before proceeding.

1. Input sharp enough? The architecture proposal must contain three things: a defined stack (languages, frameworks, infrastructure), a stated scale target (users, requests/sec, data volume), and a team size (who maintains this). If any are missing, ask one mandatory question before proceeding. Not optional. Not skippable.