[Trend Scout] ravinperera/ai-token-efficiency-playbook

[github-actions]

🔭 Trend Scout: ravinperera/ai-token-efficiency-playbook

Auto-generated by trend-scout.py — review and edit as needed.

📌 What problem it solves

Drop-in instructions, prompts, and workflows to reduce token usage across Codex, Claude Code, GitHub Copilot, Cursor, and other AI coding agents

📅 Timeline

Field	Value
Created	2026-06-17
Last pushed	2026-08-06
Stars	9
Forks	0
Open issues	13
License	None
Language	Python
Topics	ai-agents, claude-code, codex, cursor, developer-tools, github-copilot, llm, prompt-engineering, token-efficiency

✅ Strengths

• Well-tagged: ai-agents, claude-code, codex, cursor, developer-tools, github-copilot
• Primary language: Python
• Actively maintained (pushed within 30 days)

⚠️ Weaknesses / Risks

• Low star count (9) — limited community validation
• No license detected — usage rights unclear

💡 What this repo can learn

• Claude Code session patterns: this repo's Claude Code integration approach could improve claude-adapter.py's JSONL parsing — e.g., handling new session event types or extracting richer metadata from Claude Code tool-use blocks
• CLI verb patterns: a clear add/search/update/delete verb model (like memory-tool add / search / dream) could streamline the UX of query-session.py and learn.py, making them easier to invoke from hooks or scripts
• Editor integration (cursor): watch-sessions.py could be extended to detect and parse cursor session formats natively, broadening the range of AI sessions indexed into knowledge.db

README excerpt

# AI Token Efficiency Playbook

Drop-in instructions, prompts, examples, and lightweight checks to reduce wasted AI tokens across Codex, Claude Code, GitHub Copilot, Cursor, Gemini, and other AI coding agents.

This project is not just about making AI replies shorter. The main thesis is:

> Context is more expensive than reply style.

Most token waste comes from oversized context, repeated memory, noisy logs, and using the wrong model for the job. This playbook focuses on **context hygiene** and **model routing** so AI tools stay useful without carrying unnecessary token load.

## 30-Second Install

Pick your tool, copy the matching file into your repository, and commit it.

| Tool | Copy this file |
| --- | --- |
| Codex / general coding agents | `AGENTS.md` |
| Claude Code | `CLAUDE.md` |
| Gemini CLI / agents | `GEMINI.md` |
| GitHub Copilot | `.github/copilot-instructions.md` |
| Cursor | `.cursor/rules/token-efficiency.mdc` |

```bash
cp AGENTS.md /path/to/your-repo/AGENTS.md

For best results, also copy the canonical guidance in guidelines/ and the checklist in checklists/token-efficiency-checklist.md.

What This Provides

Ready-to-copy instruction files and supporting material:

.
├── AGENTS.md
├── CLAUDE.md
├── GEMINI.md
├── .github/
│   └── copilot-instructions.md
├── .cursor/
│   └── rules/
│       └── token-efficiency.mdc
├── prompts/
│   ├── tokensaver-mode.md
│   ├── debugging-mode.md
│   ├── code-review-mode.md
│   └── architecture-mode.md
├──

*(truncated)*

---

Scouted on 2026-08-07 · View on GitHub