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/ppgranger/token-saver/claude-mdgit clone --depth 1 https://github.com/ppgranger/token-saverWrote 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/ppgranger/token-saver/claude-md)<a href="https://agentmods.dev/instructions/ppgranger/token-saver/claude-md"><img src="https://agentmods.dev/badge/instructions/ppgranger/token-saver/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 | $0.00145 | $0.00145 |
| Opus 5 | $0.00072 | $0.00072 |
| Sonnet 5 | $0.00029 | $0.00029 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade B, and why
token-saver CLAUDE.md scanned grade B 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Never wrap sudo commands What it actually says
Token-Saver Plugin
Token-saver automatically compresses verbose CLI output to save tokens.
How it works
- A PreToolUse hook intercepts Bash commands matching known patterns (git, docker, npm, terraform, kubectl, etc.)
- The command output is piped through specialized compression processors
- Compressed output is returned to Claude, saving tokens while preserving critical information
Important rules
- Never wrap
token-saverCLI commands themselves (avoid infinite loops) - Never wrap interactive commands (vim, nano, ssh, etc.)
- Never wrap commands with redirections (>) or complex pipes
- Never wrap sudo commands
- Debug mode: set TOKEN_SAVER_DEBUG=true environment variable
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.
- 3d ago First seen · 16 lines · 145 tokens per session scan B e248e1acddd2
token-saver CLAUDE.md is an instructions file published in the GitHub repository ppgranger/token-saver (142 stars, last pushed 16d ago), licensed Apache-2.0. It adds 145 tokens to every session, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
packmind packmind-cli-command-structure.instructions.md
Instructions for PackmindHub/packmind: Enforce clear separation of concerns between command definition (parameters and metadata) and handler logic (validation, execution, and output) in apps/cli commands to improve testability, maintainabi... .
packmind packmind-frontend-error-management.instructions.md
Instructions for PackmindHub/packmind: A global error boundary is already configured at the root level (in root.tsx) that automatically catches all page crashes, 404s, and loader failures. This standard defines when and how to use explicit... .
packmind packmind-frontend-navigation-with-react-router.instructions.md
Instructions for PackmindHub/packmind: This codebase uses React Router v7 with organization and space scoping in URLs (e.g., /org/{orgSlug}/space/{spaceSlug}/recipes). To maintain consistency, improve maintainability, and simplify navigati... .
packmind packmind-tanstack-query-key-management.instructions.md
Instructions for PackmindHub/packmind: TanStack Query uses prefix matching to invalidate cached queries, matching keys from left to right like a file path. Properly structured query keys enable efficient cache invalidation at any scope lev... .
packmind packmind-rest-api-endpoint-design.instructions.md
Instructions for PackmindHub/packmind: Conventions for designing REST API endpoints that are predictable, self-documenting, and aligned with distinct business actions. Favors dedicated action endpoints over generic status updates, and rout... .
packmind packmind-e2e-page-object.instructions.md
Instructions for PackmindHub/packmind: Write proper PageObjects for our E2E tests .