skills/caveman-compress/SKILL.md
Caveman-compress repo docs + prose for fewer tokens. Keep substance, code, URLs, structure. Triggers: docs, memory file, repo note, dense markdown.
npx skillsauth add bjornmelin/dev-skills caveman-compressInstall 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.
Compress docs and natural language files such as AGENTS.md, todos, preferences, and repo notes into caveman-speak to reduce input tokens. Work directly in the active Codex session. Do not create backup files by default.
/caveman:compress <filepath> or user asks to compress memory file.
git status --porcelain, git diff --name-only for changes.rg, find for nearby docs; bounded semantic match for prose neighbors.request_user_input + scored recs.backtick content)/src/components/..., ./config.yaml)npm install, git commit, docker build)$HOME, NODE_ENV)CRITICAL RULE:
Anything inside ... must be copied EXACTLY.
Do not:
Inline code (...) must be preserved EXACTLY.
Do not modify anything inside backticks.
If file contains code blocks:
Original:
You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.
Compressed:
Run tests before push to main. Catch bugs early, prevent broken prod deploys.
Original:
The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.
Compressed:
Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.
.md, .mdx, .markdown, .rst, .txt, extensionless notesdevelopment
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.