2 Commits

Author SHA1 Message Date
Jesse Vincent
dd237283db Add agent-facing guardrails to contributor guidelines
Speak directly to AI agents at the top of CLAUDE.md: reframe slop
PRs as harmful to their human partner, give a concrete pre-submission
checklist, and explicitly authorize pushing back on vague instructions.
2026-03-31 14:37:13 -07:00
Jesse Vincent
c0b417e409 Add contributor guidelines to reduce agentic slop PRs
CLAUDE.md (symlinked to AGENTS.md) covers every major rejection
pattern from auditing the last 100 closed PRs (94% rejection rate):
AI slop, ignored PR template, duplicates, speculative fixes, domain-
specific skills, fork confusion, fabricated content, bundled changes,
and misunderstanding project philosophy.
2026-03-31 14:14:19 -07:00