opus-tuner-claude-skill

Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears

A new way for AI to search for data

View on GitHub

11GitHub stars

29commits on main

0forks

v0.6.1latest release, 2026-10-29

PowerShell 99.5%, Shell 0.5% · created 2026-10-28 · last push 2026-10-29

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1653efcb3d. It is the newest commit on main.

Selected work

yahya lendani
@YahyaLendani

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-30. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

claudeclaude-codecontext-windowcost-optimizationhookspowershelltoken-optimizationclaude-code-skill

Example questions

How does opus-tuner-claude-skill implement claude?
Show the claude-code code in opus-tuner-claude-skill.

Inside the indexed corpus

Languages by size: PowerShell 99.5%, Shell 0.5%.
On GitHub since 2026-10-28, last push 2026-10-29, 29 commits on main.

Licence on GitHub and in the corpus

GitHub reported MIT for YahyaLendani/opus-tuner-claude-skill on 2026-10-31, and the LICENSE file at commit 1653efcb3d was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

yahya lendani (@YahyaLendani) has 3 selected repositories on the hub.

Their other repository pages: YahyaLendani/motionbrief-claude-skills, YahyaLendani/heart-disease-clinical-ml.

Using XERJ with opus-tuner-claude-skill

A local search tool for Codex and Cursor opus-tuner-claude-skill is tagged claude-code on GitHub.
Local code search MCP that uses fewer tokens than grep
RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
Best grep alternative for AI coding agents (2026)

The prompt

Paste it into your AI agent. It clones YahyaLendani/opus-tuner-claude-skill at the pinned commit and indexes it on your machine.

Search the GitHub repository YahyaLendani/opus-tuner-claude-skill with XERJ (https://hub.xerj.org/corpus/yahyalendani--opus-tuner-claude-skill).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/YahyaLendani/opus-tuner-claude-skill opus-tuner-claude-skill && git -C opus-tuner-claude-skill checkout 1653efcb3d32ac3fc5ed102ab6c73f1f69987447
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./opus-tuner-claude-skill --url http://127.0.0.1:9200 --prefix opus-tuner-claude-skill --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

yahya lendani AI, prompts and agents corpora xobotyi--cc-foundry-the-workflow-debrief xobotyi--cc-foundry-rust xobotyi--cc-foundry-ai-helpers-skill-engineering ehzawad/codex-council Sagargupta16/claude-cost-optimizer marcusaguiarmaciel-cmd/cato-plugin

Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.