Skill Claude CodeCodex
Internet Archive Wayback Machine routing. Detects link rot, fetches closest snapshots, runs CDX timeline analysis, and submits new captures via Save Page Now (SPN2). All routes through mcp-gateway fulcrum tools (free for read; auth-aware for higher SPN2 limits). Paired skill: ia (full archive.org item…
Cursor rule
Anti-AI-tell writing rules. Apply to all prose output (docs, comments, commit messages, README content, user-facing strings).
Plugin Claude Code
Cross-media discipline so prose AND design don't read as AI-generated. Generation-time rules, a mechanical linter for prose + visual tells, a style fingerprint that injects a chosen point of view, a population-level sameness detector, and hooks that lint-on-write and ask for a style anchor when one is missing.
Command
Build or update the style fingerprint via derive-then-confirm.
Command
Lint a file or directory for visual + prose AI-tells (Tier-1 mechanical pass).
Hook
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post_tool_lint.py via python3. From MikkoParkkola/anti-ai-tell.
Hook
Runs when a session starts, executing session_fingerprint_inject.py via python3. From MikkoParkkola/anti-ai-tell.
Hook
Runs when you submit a prompt, before the agent sees it, executing active_ask_nudge.py via python3. From MikkoParkkola/anti-ai-tell.
Skill Claude CodeCodex
Make written prose not read as AI-generated, even when it is. Three-tier discipline. Tier 0 prevents AI-ese at generation time (voice constraints, banned vocabulary, rhythm rules). Tier 1 is a mechanical lint pass (lint.py) catching measured tells - banned words, em-dashes, negative parallelism, uniform rhythm…