llms.txt@docs llmstxtA
llms.txt@docs is agent-read markdown (llmstxt) from ppgranger/token-saver.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Token-Saver > Content-aware output compression for AI coding assistants. A Claude Code > and Antigravity CLI plugin that intercepts verbose CLI command output > (git, pytest, npm, terraform, kubectl, docker, and more) and compresses it > deterministically before it reaches the model, using 36 specialized > processors — one per tool family. Compression runs locally without LLM > calls or output uploads. An optional release check contacts GitHub. Savings > depend on the output and use character-based token estimates. Error > preservation is covered by representative fixtures and configurable limits. ## Start here - [Quick Start](https://github.com/ppgranger/token-saver/blob/main/README.md#quick-start): Plugin installation and first steps. - [Home](https://ppgranger.github.io/token-saver/): Overview and quick start. - [Benchmarks](https://ppgranger.github.io/token-saver/benchmarks/): 22 measured compression scenarios, gated by CI, with methodology. - [How It Compares](https://ppgranger.github.io/token-saver/comparison/): Token-Saver, RTK, and Context Mode: command compression and context retrieval. …
Read the whole file at its exact version.
How to install
mdr add ppgranger/token-saver/docs/llms.txt@git:20260919.fd3c6ddmdr add ppgranger/token-saver/docs/llms.txt@sha256:0ae36ad3b535fdb8Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_6vxfmg5vljrwom3m)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260919.fd3c6dd latest | 2026-09-19 | fd3c6dd | 7,070 B | A | view · diff |
| git:20260919.8bd664b | 2026-09-19 | 8bd664b | 6,909 B | A | view · diff |
| git:20260809.7d871fc | 2026-08-09 | 7d871fc | 4,875 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (7070 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ppgranger/token-saver · 153 stars · license Apache-2.0 · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6vxfmg5vljrwom3m GET https://markdownregistry.com/api/v1/resolve?ref=ppgranger/token-saver/docs/llms.txt GET https://markdownregistry.com/api/v1/blob/0ae36ad3b535fdb89e500b2f57de1a49131cacc832b55a8d2d903f42309b20d1
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from ppgranger/token-saver
Every file in ppgranger/token-saver