token-efficient-execution SKILL.md skillA

token-efficient-execution from galvarcus/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add galvarcus/claude-skills/token-efficient-execution@git:20261018.ddb07f4

Pins git:20261018.ddb07f4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
galvarcus/claude-skills
Path
skills/token-efficient-execution/SKILL.md
Versions recorded
2
Latest version
git:20261018.ddb07f4, committed Oct 18, 2026
First version recorded
Oct 10, 2026
Size
5,026 bytes
Repository stars
3
License
GPL-3.0

Spend the fewest tokens, tool calls, and words that still give a correct, complete, verified result. Use for every task with more than one step, even when the user does not mention cost, including code changes, debugging, refactoring, repository searches, multi-file edits, research, CI and build work, and any tool-assisted workflow, and whenever the user asks for concise, quick, cheap, or token-efficient work. Not for a one-step answer that needs no tools, such as arithmetic, a greeting, or a…

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

# Token-Efficient Execution

Use the least context, tool calls, reasoning, and output that give a correct, complete, maintainable result. Cut waste, never substance. Waste is repeated reads, broad searches, speculative calls, narration, and unrequested work. Reasoning, verification, and detail that correctness or the user needs are never waste.

## Priorities

On a conflict: correctness, then user requirements, safety, maintainability, risk-appropriate verification, token efficiency, and extra explanation. An explicit request for more detail overrides every limit below.

## Scope

Classify the task, then do that much work:

- **Trivial**: answer directly, no tools.
- **Localized**: inspect only the relevant file, function, or section.
- **Multi-file**: map dependencies before reading.
- **Repository-wide**: search first, read only the hits.
- **Research**: use the fewest authoritative sources.
- **High-risk**: spend extra on verification.

Get the minimum information a correct result needs, then stop. Never call a tool only because it is available.

## Context and Tools
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add galvarcus/claude-skills/token-efficient-execution@sha256:74bf911f365d27d3

The line at the top of this page pins the label git:20261018.ddb07f4, 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_wofk76w3bm4dnmfb.svg)](https://markdownregistry.com/a/art_wofk76w3bm4dnmfb)

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

Versions

The registry has recorded 2 versions of this file, between Oct 10, 2026 and Oct 18, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261018.ddb07f4 latest2026-10-18 ddb07f4 5,026 BA view · diff
git:20261010.aeeed132026-10-10 aeeed13 6,620 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 (5026 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

galvarcus/claude-skills · 3 stars · license GPL-3.0 · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wofk76w3bm4dnmfb
GET https://markdownregistry.com/api/v1/resolve?ref=galvarcus/claude-skills/token-efficient-execution
GET https://markdownregistry.com/api/v1/blob/74bf911f365d27d3ab256d25adb156841d51f08c5b743a5a56a46f065d0e4b79

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 galvarcus/claude-skills

code-comments SKILL.md skill
galvarcus/claude-skills · skills/code-comments/SKILL.md · Write, edit, or review comments in any file that can hold them, using this project's comment standards. Covers source…
git:20261018.86a6f57 · audit A · 3 stars
github-markdown-style SKILL.md skill
galvarcus/claude-skills · skills/github-markdown-style/SKILL.md · Create, edit, review, or improve GitHub Markdown documentation (README.md, CONTRIBUTING.md, SECURITY.md…
git:20261010.aa5a7d0 · audit A · 3 stars
handoff SKILL.md skill
galvarcus/claude-skills · skills/handoff/SKILL.md · Write or update a handoff file that lets a fresh agent pick up the current work and continue it, and resume work from…
git:20261022.e7040d3 · audit A · 3 stars
vim9script-plugin SKILL.md skill
galvarcus/claude-skills · skills/vim9script-plugin/SKILL.md · Create, edit, review, or maintain Vim plugins and Vim scripts using Vim9script per this project's standards. Use…
git:20261018.48c9179 · audit A · 3 stars
your-skill-name SKILL.md skill
galvarcus/claude-skills · templates/SKILL.md · Describe what this skill does and when Claude should use it. Include the kinds of requests, files, or situations that…
git:20261010.d9c713d · audit A · 3 stars
example-skill SKILL.md skill
galvarcus/claude-skills · templates/example-skill/SKILL.md · Demonstrate the repository's standard Agent Skill structure. Use when creating a new skill or checking the expected…
git:20261010.d9c713d · audit A · 3 stars
DESIGN.md@tests/benchmark/waypoint/solutions/design/docs DESIGN.md file
galvarcus/claude-skills · tests/benchmark/waypoint/solutions/design/docs/DESIGN.md
git:20261021.f71ac27 · audit A · 3 stars
DESIGN.md@tests/benchmark/waypoint/src/v1/docs DESIGN.md file
galvarcus/claude-skills · tests/benchmark/waypoint/src/v1/docs/DESIGN.md
git:20261021.f71ac27 · audit A · 3 stars
DESIGN.md@tests/benchmark/waypoint/src/v2/docs DESIGN.md file
galvarcus/claude-skills · tests/benchmark/waypoint/src/v2/docs/DESIGN.md
git:20261021.f71ac27 · audit A · 3 stars

Every file in galvarcus/claude-skills

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