k-tokens SKILL.md skillA

k-tokens from kasempiternal/k-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kasempiternal/k-stack/k-tokens@git:20261013.52dd772

Pins git:20261013.52dd772 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kasempiternal/k-stack
Path
kstack/skills/k-tokens/SKILL.md
Versions recorded
1
Latest version
git:20261013.52dd772, committed Oct 13, 2026
Size
6,734 bytes
Repository stars
16
License
MIT

Cut Claude Code token use. Audit reads your local transcripts and shows where tokens go (idle cache rewrites, context size, polling, Opus agents). Apply is a one-screen settings choice that merges a few documented keys into ~/.claude/settings.json and adds agent working rules to ~/.claude/CLAUDE.md. Use for /k-tokens, "audit my token use", "why is my usage so high", "cheaper agents", "subagent cache TTL", or "auto-compact window".

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

# K-tokens

!`node "${CLAUDE_SKILL_DIR}/scripts/k-tokens.js" status`

The table above came from the k-tokens script, which ran before you read this skill. It shows the current values next to the recommended ones. Do not edit `~/.claude/settings.json` or `~/.claude/CLAUDE.md` yourself. Only the apply script writes them.

Pick the mode from the argument. With no argument, show the table and ask which mode: `Audit`, `Apply`.

- `status`: show the table and stop. If it starts with `k-tokens error:`, say that line and stop.
- `audit`: go to Audit.
- `apply`: go to Apply.

## Audit

Run the audit script with the user's flags. It reads `~/.claude/projects/**/*.jsonl` on this machine and sends nothing anywhere. On a large history it can take half a minute.

```
node "${CLAUDE_SKILL_DIR}/scripts/k-tokens-audit.js" [--days N] [--project <substring>] [--json]
```

Show the report as printed, then restate the "What to change" section in your own words, most valuable first. Offer to run Apply for the settings it names. Do not read the transcripts yourself.

Notes for reading the report:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kasempiternal/k-stack/k-tokens@sha256:c7c5b1ff72b87514

The line at the top of this page pins the label git:20261013.52dd772, 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_cyi7ecw6y656ovgh.svg)](https://markdownregistry.com/a/art_cyi7ecw6y656ovgh)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 13, 2026.

versioncommittedcommitsizeaudit
git:20261013.52dd772 latest2026-10-13 52dd772 6,734 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 (6734 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

kasempiternal/k-stack · 16 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cyi7ecw6y656ovgh
GET https://markdownregistry.com/api/v1/resolve?ref=kasempiternal/k-stack/k-tokens
GET https://markdownregistry.com/api/v1/blob/c7c5b1ff72b875147ee281b259e63774b3abd930958aa46a7638781c5552d933

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 kasempiternal/k-stack

k-cursor-architect SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-cursor-architect/SKILL.md · Delegate focused implementation or investigation from Claude Code to the Cursor Agent CLI (cursor-agent) running Grok…
git:20260929.5c87f77 · audit A · 16 stars
k-design SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-design/SKILL.md · Design before implementing. Opus produces the data shape, interface, file plan, failure cases, tests, and verification…
git:20260929.5c87f77 · audit A · 16 stars
k-e2e-qa SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-e2e-qa/SKILL.md · E2E and UI verification workflows. AgentController for native macOS apps (mcp__agentcontroller__*) and for iOS…
git:20260929.5c87f77 · audit A · 16 stars
k-effort SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-effort/SKILL.md · Switch K-stack's routing level the way /effort switches session effort. Levels are lean < balanced < quality, plus burn…
git:20261007.940a9bf · audit A · 16 stars
k-explore SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-explore/SKILL.md · Explain how a subsystem works, trace a runtime flow, answer where code should live, or dig up why something was built…
git:20261007.f28effe · audit A · 16 stars
k-gpt-architect SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-gpt-architect/SKILL.md · Delegate focused implementation or investigation from Claude Code to the Codex MCP. Use when the user invokes…
git:20260929.5c87f77 · audit A · 16 stars
k-mode SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-mode/SKILL.md · Kasempiternal's Claude-only engineering mode. The lead plans and reviews, work is routed by role to Sonnet or Opus…
git:20261007.f28effe · audit A · 16 stars
k-review SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-review/SKILL.md · Review a diff with Opus reviewers on separate lenses (correctness, simplification, security and data, tests), judge the…
git:20260930.472d1b9 · audit A · 16 stars
k-setup SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-setup/SKILL.md · Configure K-stack's role-to-tier routing (which Haiku, Sonnet or Opus effort each role uses). Writes a managed…
git:20261013.ab7a650 · audit A · 16 stars
k-spectre SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-spectre/SKILL.md · Parallel research with synthesis and independent claim validation. Use for multi-source research questions, answers…
git:20260929.5c87f77 · audit A · 16 stars
k-write SKILL.md skill
kasempiternal/k-stack · kstack/skills/k-write/SKILL.md · K-stack prose rules for docs, READMEs, RFCs, PR descriptions, commit bodies, code comments, and agent replies. Cuts AI…
git:20260929.5c87f77 · audit A · 16 stars

Every file in kasempiternal/k-stack

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