savings SKILL.md skillB

savings from thanatos9404/llmslim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add thanatos9404/llmslim/savings@git:20261017.b0ec806

Pins git:20261017.b0ec806 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
thanatos9404/llmslim
Path
plugins/llmslim/skills/savings/SKILL.md
Versions recorded
1
Latest version
git:20261017.b0ec806, committed Oct 17, 2026
Size
1,032 bytes
Repository stars
17
License
MIT

Show how many input tokens the LLMSlim proxy kept out of Claude Code's requests.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Run `llmslim proxy stats`, adding `--days $ARGUMENTS` if the user gave a number of days. If `llmslim` isn't on the
PATH, run `uvx --from "llmslim[proxy]" llmslim proxy stats` instead.

Report the numbers as the command prints them: requests changed, outputs compressed and how often they were replayed,
input tokens before and after, and tokens not sent. Don't turn them into a dollar figure unless the user gives their
price per million input tokens; then rerun with `--price-per-mtok <price>`. Note that this estimate is before any
prompt-caching discount, so the billed saving is smaller when most of those tokens would have been cache reads.

If every number is zero, Claude Code probably wasn't started with `llmslim wrap claude`. Point the user to
`/llmslim:wrap-claude`.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add thanatos9404/llmslim/savings@sha256:6e89c23acd18a811

The line at the top of this page pins the label git:20261017.b0ec806, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yt2ol5otnsxu2pi3.svg)](https://markdownregistry.com/a/art_yt2ol5otnsxu2pi3)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 17, 2026.

versioncommittedcommitsizeaudit
git:20261017.b0ec806 latest2026-10-17 b0ec806 1,032 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: Frontmatter declares a name
  • pass: Frontmatter block present
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1032 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

thanatos9404/llmslim · 17 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yt2ol5otnsxu2pi3
GET https://markdownregistry.com/api/v1/resolve?ref=thanatos9404/llmslim/savings
GET https://markdownregistry.com/api/v1/blob/6e89c23acd18a811017bfdb4f53a8bad30de8b6663ec89b7e4c4d91fa8b6fab4

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from thanatos9404/llmslim

wrap-claude SKILL.md skill
thanatos9404/llmslim · plugins/llmslim/skills/wrap-claude/SKILL.md · Set up llmslim wrap claude, which runs Claude Code through a local proxy that shortens long test logs, build output and…
git:20261017.52a6128 · audit B · 17 stars
AGENTS.md@web AGENTS.md file
thanatos9404/llmslim · web/AGENTS.md
git:20261008.38e1dbd · audit A · 17 stars
CLAUDE.md@web CLAUDE.md file
thanatos9404/llmslim · web/CLAUDE.md
git:20260714.5c21d11 · audit B · 17 stars

Every file in thanatos9404/llmslim

Other files named savings

savings SKILL.md skill
stuinfla/ruvnet-brain · plugin/skills/savings/SKILL.md · Show the MetaHarness routing ledger inline — which model each task was routed to, what it displaced, and the percentage…
git:20260727.720a4bf · audit A · 75 stars
savings SKILL.md skill
rossoctl/context-guru · context-guru-plugin/skills/savings/SKILL.md · Moved to /context-guru:insights savings (how much Context Guru saved). Kept for one release so existing habits still…
git:20261015.3051da9 · audit A · 70 stars

Browse by kind, by grade B, or by owner.