toksave: Instructions file for Claude Code

CLAUDE.md

toksave CLAUDE.md is an instructions file for Claude Code from agungprasastia/toksave. It costs 897 tokens per session, scanned A, original, MIT.

Repository instructions for TokSave, a Rust command-line tool that installs and connects token-saving tools to AI coding agents. They cover commands, architecture, supported agents, and required checks.

In plain words
What is it for?
Use them when changing TokSave’s CLI, agent and tool registry, installation flows, diagnostics, or Rust code, then run its formatting, lint, build, and test commands.
Why use it?
They help an agent follow the project’s installation conventions and verify changes with the same checks used by its continuous-integration system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is agungprasastia/toksave's own configuration. It tells Claude Code how to work on toksave 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 toksave configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agungprasastia/toksave. 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/agungprasastia/toksave/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/agungprasastia/toksave

Made for: Claude Code.

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 toksave CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agungprasastia/toksave/claude-md/github.svg)](https://agentmods.dev/instructions/agungprasastia/toksave/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/agungprasastia/toksave/claude-md"><img src="https://agentmods.dev/badge/instructions/agungprasastia/toksave/claude-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 toksave CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/agungprasastia/toksave/claude-md"><img src="https://agentmods.dev/badge/instructions/agungprasastia/toksave/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 897 This file is loaded in full into every session.
When invoked 897 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00897 $0.00897
Opus 5 $0.00449 $0.00449
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00090 $0.00090

Measured 8d ago against content hash 0caf4f4a12d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

toksave 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 8d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 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

TokSave is a Rust CLI (src/) that installs and wires token-saving tools into AI coding agents. It targets 9 agents (Claude Code, OpenCode, Codex, Antigravity, GitHub Copilot, Droid, Devin, Warp, Cursor CLI) and wires RTK, Caveman, CodeGraph, Context-Mode, Ponytail, and Principles.

Node.js >= 22 is needed for full install flows involving npm-based tools (context-mode, codegraph, ponytail).

Commands

cargo run -- --help
cargo run -- doctor --offline
cargo run -- doctor --fix
cargo check
cargo fmt --check
cargo clippy --all-targets -- -D warnings
cargo test
cargo test --test agents
cargo test --lib
cargo build --release

CI runs cargo check, cargo fmt --check, cargo clippy, cargo test, and cross-platform release builds.

Architecture

  • src/main.rs is the executable entrypoint. It handles early hook dispatch, parses CLI args, dispatches command modules, and exits with returned status code.
  • src/cli.rs owns clap CLI setup and argument parsing. Default command is init.
  • src/registry.rs is the central agent/tool matrix. Contains ALL_AGENTS, ALL_TOOLS, AgentId, ToolId, and RunOpts.
  • src/commands/ contains user-facing command flows:
    • init detects agents, checks tool dependencies, prompts/auto-selects targets, installs tools, and wires configs.
    • doctor checks agent wiring, tool health, and tool versions; --offline skips remote latest-version checks, and --fix runs tool repair for unhealthy tools.
    • update reinstalls tools with upgrade semantics.
    • uninstall unwires selected agents/tools and cleans empty configs.
    • disable, self_update, runmcp, hooks, index are specialized helper commands.
  • src/agents/ contains per-agent config writers. These modules know each agent's file layout and implement all tool-specific wiring/unwiring for that agent.
  • src/tools/ contains tool installation, health check, and repair logic (rtk, caveman, codegraph, context_mode, ponytail, principles).
  • src/util/paths.rs centralizes cross-platform home/config/cache paths (dirs crate). Prefer it over inline path construction for agent config locations.
  • src/util/json.rs and src/util/toml.rs provide JSON/TOML config handling and pruning helpers (write_json_pruned, write_toml_pruned).
  • src/util/manifest.rs tracks wires in TOKSAVE_CACHE_DIR or ~/.cache/toksave/manifest.json.

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 897 tokens per session scan A 0caf4f4a12d6

Subscribe to this mod's changes

toksave CLAUDE.md is an instructions file published in the GitHub repository agungprasastia/toksave (5 stars, last pushed 20d ago), licensed MIT. It adds 897 tokens to every session, about $0.0045 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

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens