report-limit SKILL.md skillA

report-limit from ww-w-ai/super-token-saver is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ww-w-ai/super-token-saver/report-limit@git:20260927.7f791de

Pins git:20260927.7f791de in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ww-w-ai/super-token-saver
Path
skills/report-limit/SKILL.md
Versions recorded
5
Latest version
git:20260927.7f791de, committed Sep 27, 2026
First version recorded
Sep 6, 2026
Size
7,465 bytes
Repository stars
35
License
Apache-2.0

Report your 5h and weekly limit data (Claude Code or Codex) - we''re mapping how many tokens a limit is, which neither host publishes.

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

Dual-host. Detect the host you are running under:

- **Claude Code**: Claude Code does not state its 5h window, so the script rebuilds it from cached timelines and statusline samples. Ask the plan (below), then run with `--host claude`.
- **Codex**: Codex states each limit outright — used percent, window length, reset instant. The script pairs every recorded limit window with the tokens spent inside it. Do not ask the plan: Codex records it. Run with `--host codex`.
- Resolve `PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT}}"`, falling back to two levels above this skill's directory if both are unset.

Report 5-hour and weekly limit windows to GitHub Discussions. Pure rule-based — no LLM reasoning needed.

## Help

**ONLY show help if the user's argument literally contains the word "help" (e.g. `/report-limit help`). If no argument or any other argument is given, SKIP this section entirely and proceed to execution.**

If the user provides "help" as argument, show usage summary and stop:

```
/report-limit — Report your rate limit data

Help map the unpublished rate-limit formula. This skill collects
your 5-hour windows from cached timeline data and opens a pre-filled
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ww-w-ai/super-token-saver/report-limit@sha256:e1fc4df0b83f4ab2

The line at the top of this page pins the label git:20260927.7f791de, 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_egjkm562ua7kasuz.svg)](https://markdownregistry.com/a/art_egjkm562ua7kasuz)

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

Versions

The registry has recorded 5 versions of this file, between Sep 6, 2026 and Sep 27, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20260927.7f791de latest2026-09-27 7f791de 7,465 BA view · diff
git:20260927.f6d287c2026-09-27 f6d287c 7,258 BA view · diff
git:20260927.09de2642026-09-27 09de264 7,264 BA view · diff
git:20260927.ef4d33f2026-09-27 ef4d33f 5,883 BA view · diff
git:20260906.c90c77f2026-09-06 c90c77f 5,565 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7465 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

GitHub

ww-w-ai/super-token-saver · 35 stars · license Apache-2.0 · pushed 2026-09-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_egjkm562ua7kasuz
GET https://markdownregistry.com/api/v1/resolve?ref=ww-w-ai/super-token-saver/report-limit
GET https://markdownregistry.com/api/v1/blob/e1fc4df0b83f4ab253d0ef8f9a4c216a94fa53839e2142c4e3b7dbb43f34c714

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 ww-w-ai/super-token-saver

CLAUDE.md CLAUDE.md file
ww-w-ai/super-token-saver · CLAUDE.md
git:20260930.f07bf00 · audit A · 35 stars
llms.txt llms.txt file
ww-w-ai/super-token-saver · llms.txt
git:20260825.3d37cc5 · audit A · 35 stars
s-compact SKILL.md skill
ww-w-ai/super-token-saver · skills/s-compact/SKILL.md · Session handoff for the next session — write-side pair of /s-continue. Triggers on "s-compact", "session handoff"…
git:20260825.3d37cc5 · audit A · 35 stars
s-continue SKILL.md skill
ww-w-ai/super-token-saver · skills/s-continue/SKILL.md · Cheaper and faster than /compact. Restores previous session context from Claude Code AND Codex transcripts by reading…
git:20260930.f07bf00 · audit A · 35 stars
setup-git-lite SKILL.md skill
ww-w-ai/super-token-saver · skills/setup-git-lite/SKILL.md · Disable Claude Code built-in git instructions and inject a curated 280-tok minimum via SessionStart hook. Saves ~2,200…
git:20260825.3d37cc5 · audit A · 35 stars
setup-statusline SKILL.md skill
ww-w-ai/super-token-saver · skills/setup-statusline/SKILL.md · Live token counter in your CLI. Shows real-time input/output/cache token counts in the Claude Code status bar
git:20260906.c90c77f · audit A · 35 stars
usage-view SKILL.md skill
ww-w-ai/super-token-saver · skills/usage-view/SKILL.md · Know exactly what you spent (Claude Code) or how much of your Codex limit you have used (Codex). Interactive HTML…
git:20260901.e107cd3 · audit A · 35 stars

Every file in ww-w-ai/super-token-saver

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