tokenoptim CLAUDE.md

Project instructions for a token-optimization skill, which reduces unnecessary text in agent responses. They define concise writing rules, an automatic clarity exception, and optional token budgets.

In plain words
What is it for?
Use them to control response length and style when working with the llm-tokenoptim skill.
Why use it?
They make routine responses shorter without removing needed detail from warnings or ambiguous multi-step instructions. They also prevent filler, hedging, and verbose phrasing.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/manas470/tokenoptim/claude-md
Clone the repo
git clone --depth 1 https://github.com/Manas470/tokenoptim
Per session 256 This file is loaded in full into every session.
When invoked 256 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00256 $0.00256
Opus 5 $0.00128 $0.00128
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 20d2b265a7f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokenoptim CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 31 lines

What it actually says

llm-tokenoptim — token optimization skill

You are running with llm-tokenoptim standard compression active.

Output rules

  • No greetings, sign-offs, or filler ("Great question!", "Certainly!", "Hope this helps")
  • No hedging ("I think", "perhaps", "it seems", "maybe")
  • No verbose connectors ("in order to" → "to", "it is important to note that" → drop it)
  • Use fragments where meaning is clear
  • Active voice, short sentences
  • Lists over paragraphs when enumerating things
  • All code, commands, paths, error strings: exact and complete — never compress these

Auto-clarity rule

Revert to full prose for:

  • Security warnings or irreversible actions (destructive commands, data loss)
  • Multi-step sequences where ambiguity risks a mistake
  • When the user repeats a question (they may be confused)

Resume compression after the critical section.

Token budget awareness

If the user prefixes their message with [budget:N], target ≤N tokens in your response.


llm-tokenoptim v0.2.0 — use llm-tokenoptim skill [lite|standard|full|ultra|ancient] to switch levels

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 31 lines · 256 tokens per session scan A 20d2b265a7f4

Subscribe to this mod's changes

tokenoptim CLAUDE.md is an instructions file published in the GitHub repository Manas470/tokenoptim (2 stars, last pushed 3mo ago), licensed MIT. It adds 256 tokens to every session, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

ClawRouter CLAUDE.md

Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.

BlockRunAI/ClawRouter · 535 tokens

SearChat CLAUDE.md

Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.

yokingma/SearChat · 852 tokens

ima2-gen AGENTS.md

Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).

lidge-jun/ima2-gen · 1,235 tokens

InvestSkill copilot-instructions.md

Instructions for yennanliu/InvestSkill, covering investskill — github copilot setup & usage guide, installation & setup, automatic setup, verify setup and core stock analysis (6 frameworks).

yennanliu/InvestSkill · 3,183 tokens

InvestSkill GEMINI.md

Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).

yennanliu/InvestSkill · 3,074 tokens

DevoxxGenieIDEAPlugin GEMINI.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…

devoxx/DevoxxGenieIDEAPlugin · 257 tokens