Borrowing it
Nothing to install: this file belongs to ppgranger/token-saver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ppgranger/token-saver/main/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/ppgranger/token-saver/agents-md"><img src="https://agentmods.dev/badge/instructions/ppgranger/token-saver/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.
<a href="https://agentmods.dev/instructions/ppgranger/token-saver/agents-md"><img src="https://agentmods.dev/badge/instructions/ppgranger/token-saver/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01093 | $0.01093 |
| Opus 5.5 | $0.00437 | $0.00437 |
| Sonnet 5.5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
token-saver AGENTS.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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Token-Saver
Token-Saver is a Python 3.10+ CLI-output compressor, with Claude Code and Antigravity adapters and a Jekyll documentation site. Compression runs locally and deterministically, without an LLM or network call in the compression path.
Read the relevant instructions
This file applies to the repository. A nested AGENTS.md adds guidance for its
directory; read it before editing there. CLAUDE.md describes plugin behavior
and shell exclusions. Keep those guarantees consistent with code and tests.
Python style
Use the Google Python Style Guide
as the review standard; CONTRIBUTING.md documents project tooling and exceptions.
- Format Python to 80 columns. Preserve literal fixture data when wrapping would change its meaning; justify any narrow exception rather than disabling a rule.
- Import modules by absolute package names and qualify their members. Typing
symbols from
typing,typing_extensions, andcollections.abcare exempt. - Write meaningful Google-style docstrings for public interfaces and nontrivial
behavior. Describe relevant
Args,Returns/Yields,Raises, and publicAttributes; do not mechanically restate signatures or test names. - Keep comprehensions simple: one
forclause and at most one filter. Use loops for nested traversal and preserve processing order. - Catch specific exceptions. A broad catch requires an explicit isolation boundary or re-raise; record suppressed failures without commands, captured output, secrets, exception text, or traceback locals.
- Include the repository's Apache 2.0 header in Python files. Preserve
third-party copyright and license notices, including
.pylintrc. Explain unavoidable local suppressions beside the relevant code.
Design and compatibility
- Keep parsing/compression, orchestration, persistence, CLI presentation, and platform integration separate. Prefer small interfaces and injected dependencies where a real boundary exists; avoid abstract wrappers that add no behavior or independent test seam.
- Extend the processor contract for a new command family instead of adding command-specific branches to the engine or platform hooks.
- Preserve public CLI behavior, processor extension points, return shapes, and
installed-tree imports during refactors. New
srcsubpackages need explicit packaging and installer coverage; current copying discovers top-level source modules and processor modules. - Preserve failure details and secret redaction ahead of compression ratios. A redacted result must never be replaced by its unredacted input merely because a size threshold was not met.
- Follow the existing Python 3.10 syntax and standard-library runtime approach. Use explicit UTF-8 for text files and text subprocess output.
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.
- 1mo ago First seen · 98 lines · 1,093 tokens per session scan A 916878c468a3
token-saver AGENTS.md is an instructions file published in the GitHub repository ppgranger/token-saver (161 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,093 tokens to every session, about $0.0044 per session on Opus 5.5. 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 2026-09-20.
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).
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.
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).
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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.