aeo-optimization
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
$ npx -y skills add alinaqi/claude-bootstrap --skill context-shunt --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/context-shuntContext preview
The summary Claude sees to decide when to auto-load this skill.
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
name: context-shunt description: Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings) when-to-use: When answering a question that requires reading large or many files, reviewing logs, or scanning generated output — anything you don't need to edit user-invocable: false effort: low
Reading big files into context is the most expensive thing an agent does for the least reasoning value. The shunt hands those reads to a cheap worker model (`bulk-read`) that answers a question about the files and returns a compact summary. The raw bytes never enter this session's context.
This is orthogonal to whole-turn routing (srooter / `route-task`): those pick the model for the *turn*; the shunt trims what a *tool call* pulls into context when the turn is legitimately here.
A shunt answer is for understanding, not for producing a diff.
bulk-read "how does token refresh work?" src/auth/session.ts src/auth/refresh.ts bulk-read "which config keys are read at startup?" $(git ls-files 'config/*.yaml')
`bulk-read` prints structured bullets citing `path:line`, or `NOT FOUND IN PROVIDED FILES`. A token-savings report goes to stderr.
Env vars or `~/.claude/shunt.conf` (see `templates/shunt.conf`):
The `context-shunt-gate` PreToolUse hook enforces the thresholds; this skill tells you when to reach for `bulk-read` yourself.
Turn Claude Code into a self-reviewing, test-enforced engineering system that remembers context across sessions — then route work across 13 models from a single dashboard.
Repo: alinaqi/claude-bootstrap
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing