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.
npx agentmods add instructions/alidhibi/ccto/claude-mdgit clone --depth 1 https://github.com/alidhibi/cctoWrote 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.
[](https://agentmods.dev/instructions/alidhibi/ccto/claude-md)<a href="https://agentmods.dev/instructions/alidhibi/ccto/claude-md"><img src="https://agentmods.dev/badge/instructions/alidhibi/ccto/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01752 | $0.01752 |
| Opus 5 | $0.00876 | $0.00876 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
ccto 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
CCTO (Claude Code Token Optimizer) reduces token consumption by 60–80% when using Claude Code by combining:
- Local semantic indexing — tree-sitter AST chunking + local embeddings (offline RAG)
- MCP Server — exposes
semantic_search,smart_read,project_outline,memory_recalltools to Claude - Persistent memory — session memory via Claude Code hooks
- Output compression — compresses logs, test output, build artifacts
- Metrics — tracks and reports tokens saved
Target project languages: TypeScript, JavaScript, Python, PHP, CSS, Bash/Shell, MySQL, MongoDB.
Commands
# Install all workspace dependencies
pnpm install
# Build all packages (ESM + types via tsup)
pnpm build
# Build in watch mode (development)
pnpm dev
# Run all tests
pnpm test
# Run tests in watch mode
pnpm test:watch
# Run a single test file
pnpm test packages/core/src/indexer/__tests__/indexer.test.ts
# Run tests matching a pattern
pnpm test -- --grep "semantic_search"
# Lint (auto-fix)
pnpm lint
# Format (auto-fix)
pnpm format
# Type check without emitting
pnpm typecheck
# Clean all build artifacts
pnpm clean
Per-package commands work the same way from within each packages/<name>/ directory.
Monorepo Structure
ccto/
├── packages/
│ ├── shared/ # Shared types, constants, utilities (no external deps)
│ ├── core/ # All business logic (indexer, embeddings, store, memory, metrics, config)
│ ├── mcp-server/ # MCP stdio server — exposes tools to Claude
│ └── cli/ # User-facing CLI (commander + ink TUI)
├── docs/ # architecture.md, mcp-tools.md, hooks.md, faq.md
└── examples/ # Example projects for e2e testing
Dependency flow: cli → core → shared; mcp-server → core → shared. Inter-package references use workspace:*.
Package Responsibilities
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.
- 4d ago First seen · 164 lines · 1,752 tokens per session scan A d386015f6f01
ccto CLAUDE.md is an instructions file published in the GitHub repository alidhibi/ccto (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,752 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).