Chris Williams

Dead simple login processor for express.js

Freshness checker for Agent Skills — like npm outdated for skill knowledge

The missing quality toolkit for Agent Skills — like npm outdated for skill knowledge

Converts prosecution findings into permanent defenses — the compounding closer (P7).

Ticket executability gate (P2) — a cheap-tier LLM checks whether a ticket is self-contained before a build agent starts.

Mines human PR review objections into structured prosecution lenses (C13).

N-version programming for failing tests — fan N LLM completions, group by agreement, recommend the smallest consensus fix (C7/P4).

Validates the verifiable claims inside skills — cache invalidation for skill rot (P7/C10).

Audits a spec for acceptance criteria that lack a concrete verification method (C1/P1).

Machine-checkable fitness-to-build gate — denies starting a high-risk P4 build in a degraded (context-rot) session unless an audited override is recorded (C13).

Scheduled re-prosecution of hot paths — every frontier model release as a free re-audit (C12).

Deterministic per-ticket model assignment from the ticket DAG and ledger — no LLM calls (D1).

ADLC native integration for Google Gemini (antigravity/jetski)

Mine skills and agents from a codebase as durable, reusable SKILL.md artifacts

Adversarial, ship/no-ship code review of a git diff or branch — runs against any LLM (API or local CLI agent) and returns structured findings