agentmods.dev

claude-token-optimizer: Instructions file for Codex

AGENTS.md

claude-token-optimizer AGENTS.md is an instructions file for Codex, OpenCode from nadimtuhin/claude-token-optimizer. It costs 1,421 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Token Optimizer, a command-line tool that reduces the project guidance Claude Code loads at session start. It organizes longer guidance into files that can be loaded when needed.

In plain words
What is it for?
It is for setting up and maintaining a project’s CLAUDE.md instructions, measuring their token use, compressing them, and pruning old content.
Why use it?
It helps keep automatically loaded instructions smaller and moves finished work or old notes out of the main guidance file.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is nadimtuhin/claude-token-optimizer's own configuration. It tells Codex and OpenCode how to work on claude-token-optimizer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-token-optimizer configures →

not rated 633repo +6 today A scan 1,421 tokens original MIT
View source ↗ nadimtuhin/claude-token-optimizer npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to nadimtuhin/claude-token-optimizer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nadimtuhin/claude-token-optimizer/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nadimtuhin/claude-token-optimizer

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-token-optimizer AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nadimtuhin/claude-token-optimizer/agents-md/github.svg)](https://agentmods.dev/instructions/nadimtuhin/claude-token-optimizer/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nadimtuhin/claude-token-optimizer/agents-md"><img src="https://agentmods.dev/badge/instructions/nadimtuhin/claude-token-optimizer/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-token-optimizer AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nadimtuhin/claude-token-optimizer/agents-md"><img src="https://agentmods.dev/badge/instructions/nadimtuhin/claude-token-optimizer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,421 This file is loaded in full into every session.
When invoked 1,421 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01421 $0.01421
Opus 5.5 $0.00568 $0.00568
Sonnet 5.5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured 13d ago against content hash b3d9ffa61bbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-token-optimizer AGENTS.md scanned grade A with 1 finding 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 13d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Unit test the pure functions. For command behaviour, spawn `bin/cto.js` with `spawnSync` in a temp directory, as `tests/compress.test.js` and `tests/prune.test.js` do.
AGENTS.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

claude-token-optimizer (CLI: cto) shrinks what Claude Code loads at session start. It sets up a small CLAUDE.md with on-demand doc folders, measures auto-loaded tokens, and moves finished tasks and old session notes out of CLAUDE.md. On the author's RedwoodJS project startup went from about 11,000 tokens to about 800. Token counts use the Claude 2 tokenizer, so they are estimates.

Use cto in a project

Run from the root of the user's project with Node 20+. Every command below uses npx -y claude-token-optimizer; if cto is installed globally, cto works the same.

Safety rules, read before writing anything:

  • Copy CLAUDE.md to a safe place first. compress and prune each write <file>.bak, but a second run replaces the first .bak, so after chaining them only the last change can be undone.
  • Never pass --force to init on a user's project. It replaces CLAUDE.md and the support files with no backup.
  • If the project has no CLAUDE.md, init writes .claudeignore, .claude/COMMON_MISTAKES.md, .claude/QUICK_START.md, .claude/ARCHITECTURE_MAP.md and docs/INDEX.md fresh, replacing any that already exist. Check for those files first and back them up.
  • compress is lossy: it truncates long lists and strips HTML comments, including tool markers such as <!-- OMC:START -->. Read the --dry-run output before applying.

Steps:

  1. npx -y claude-token-optimizer measure shows auto-loaded tokens, file by file.
  2. npx -y claude-token-optimizer init --yes --framework <name> creates CLAUDE.md, .claude/, docs/ and .claudeignore. Frameworks: express, nextjs, react, vue, nuxtjs, angular, svelte, nestjs, django, fastapi, rails, laravel, go, spring-boot. Leave out --framework to auto-detect. If CLAUDE.md exists, init appends only the missing cto sections and leaves the support files alone.
  3. npx -y claude-token-optimizer prune --dry-run, then prune --yes. Moves completed-task and dated session-note sections into .claude/completions/ and .claude/sessions/archive/, and drops empty sections. --days <n> limits it to session notes older than n days.
  4. npx -y claude-token-optimizer compress --dry-run, then compress --yes only if the preview is acceptable.
  5. npx -y claude-token-optimizer audit --json checks structure and token health. It exits 1 when there are errors. audit --fix creates missing files for failing checks.
  6. npx -y claude-token-optimizer diff shows the token delta between CLAUDE.md and CLAUDE.md.bak.

Read the full file on GitHub · 70 lines

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. 13d ago First seen · 70 lines · 1,421 tokens per session scan A b3d9ffa61bbd

Subscribe to this mod's changes

claude-token-optimizer AGENTS.md is an instructions file published in the GitHub repository nadimtuhin/claude-token-optimizer (633 stars, last pushed today), licensed MIT. It adds 1,421 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Claude CodeMemory and contextai-assistantautomationdeveloper-toolsdocumentationtoken-optimization
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens