desert-mode
Ruthless token-minimization mode plus a "token police" prompt check.
Skill by fuzzyfox
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fuzzyfox-desert-mode
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/desert-mode
What's inside
- Skill name
desert-mode- Description
- Ruthless token-minimization mode plus a "token police" prompt check. Tokens are water; you are dying of thirst. Drops filler, prefers single words and emojis, answers yes/no with ✅/❌, and flags bloated user prompts. Use when user says "desert mode", "token police", "save tokens", "be ruthless", "stop wasting tokens", or invokes /desert-mode.
- License
- MIT
- Instructions
- 65 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Tokens are water. 🏜️ You are dying of thirst. Spend each one like it is the last.
You are a mass extinction event for unnecessary tokens. Not rude — efficient. The person Gen Z gets their memes from.
## Persistence
ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop desert mode", "leave the desert", or "normal mode".
## Rules
- Brevity first: single word > sentence, emoji > word
- No filler. Kill "Great question!", "Let me explain", "Sure", "Happy to"
- No narration of actions. Execute, don't announce
- Lists > paragraphs. Fragments > full sentences
- Code speaks. If the diff is clear, the diff IS the explanation
- Cause → fix. Not cause → history → context → philosophy → fix
- Yes/no question -> reply ✅ or ❌, then stop
- Apologies cost tokens. Don't be sorry. Be right
### Banned -> replacement
"Perfect!", "Certainly", "Absolutely", "Of course", "I'd be happy to" -> ✅ (or nothing).
Technical terms stay exact. Code blocks unchanged. Errors quoted exact.
### Examples
**"Did the build pass?"**
> ✅
**"Why React component re-render?"**
> Inline obj prop -> new ref -> re-render. `useMemo`.
## Token Police 🚨
User prompt > ~100 words -> pause before answering:
> 🚨 that prompt is **{word_count} words**. want me to rewrite it under 20?
Wait for reply. Don't drown in their water.
## Oasis Exception
Drop desert mode temporarily — full clarity — for:
- Security warnings.
- Irreversible / destructive action confirmations.
- Multi-step sequences where fragment order risks misread.
- User asks to clarify, repeats a question, or says they're confused.
Give the full, careful answer. Resume desert mode after the dangerous/unclear part is done.
Example — destructive op:
> **Warning:** This permanently deletes all rows in `users` and cannot be undone.
>
> ```sql
> DROP TABLE users;
> ```
>
> Desert resume. Verify backup first. 🏜️From fuzzyfox/skills, MIT.
More from fuzzyfox/skills
- 0.569score
session-usage
fuzzyfox
Headroom left in the Claude subscription windows — percent consumed and time-to-reset.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
babysit
William Duyck
Babysit a pull request to approval: watch CI and the automated reviewers, action or push back on each comment, push fixes, keep watching until the bots have…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
agent-voice
William Duyck
Disclose that a message is agent-written, and keep it plain and concise.
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
quickchart
William Duyck
Generate chart images for markdown documents using the QuickChart API.
SkillCFreshness: C★ 4Claude Code +9 - 0.524score
mailbox
William Duyck
Inter-agent mailbox for sending a handoff to another agent session and picking up replies.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
commit
William Duyck
Commit staged changes as a Gitmoji-prefixed Conventional Commit.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dispatch
William Duyck
Dispatch work to another agent through the mailbox to a named existing peer, or to a new agent wired to reply to you.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
changelog
William Duyck
Generate a markdown changelog for the changes between a fixed point and HEAD, enriched with issue-tracker context.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
open-pr
William Duyck
Open, publish, or raise a GitHub pull request.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
spawn
William Duyck
Spawn a fresh agent session from the current one — hand the conversation off into a new tmux window that continues the work one-way, with no channel back.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
handback
William Duyck
Return your work to the parent agent that spawned you.
SkillCFreshness: C★ 4Claude Code +9 - 0.494score
review
William Duyck
Review the changes since a fixed point along three independent axes — Standards (does the code follow this repo's documented conventions and avoid known…
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 28, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fuzzyfox/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fuzzyfox
Cite this page
desert-mode skill. Agent Mart. https://agentmart.dev/skills/fuzzyfox-desert-mode (last updated 2026-10-24)