archive/skills/bun-audit/SKILL.md
Shared Bun audit/remediation router. Use when auditing a repo for Bun-first correctness, explaining findings, listing rules, planning safe fixes, applying low-risk remediations, or validating Bun-related changes.
npx skillsauth add bjornmelin/dev-skills bun-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill as a thin router over the native codex-dev bun engine. Do not
duplicate rules or remediation logic here; bun-dev owns rule text and
references.
audit: run codex-dev --json bun audit --root <repo>.rules list: run codex-dev --json bun rules list.rules show <rule-id>: run codex-dev --json bun rules show <rule-id>.fixes plan: run codex-dev --json bun fixes plan --root <repo>.fixes apply: run codex-dev --json bun fixes apply --root <repo>.validate plan: run codex-dev --json bun validate plan --root <repo>.validate run: run codex-dev --json bun validate run --root <repo> --fail-on warn.benchmark: run codex-dev --json bun benchmark --root <repo>.bun-dev as the source of truth for rules and reference snapshots.codex-dev bun ...; it is the sole supported Bun audit and remediation CLI.fixes apply, validate run, or references sync in parallel
against the same repo or skill root.--write-cache.fixes plan and surface the tradeoff.development
Pre-PR multi-model review, parallel opus and codex exec adversarial lanes, then adversarial verification of merged findings. Read-only. Use before shipping nontrivial diffs.
tools
Independent gpt-5.6 diff review via the Codex CLI, normal or steerable adversarial with JSON findings. Use before shipping nontrivial changes.
development
Delegate implementation, investigation, or bulk work to gpt-5.6 codex via pinned codex exec. Use for clear-spec builds, migrations, debugging, or any task MODELS.md routes to codex.
development
Adversarial pre-mortem: imagine the plan failed, work backwards to surface risky assumptions + irreversible bets, then harden them. Proactively offer it (after the current request; confirm first) before a hard-to-reverse or one-way-door call (API, schema, framework, a hire), an all-upside plan, or unvalidated assumptions. Also on request.