Cost Mode
If you're doing a lot of back and forth with Claude and watching token costs add up, this cuts output by 40 to 70 percent without losing technical accuracy. It strips pleasantries, hedging, and restated questions while keeping all the actual substance. Three intensity levels from professional brevity to telegraphic fragments. Also suggests cheaper models when appropriate, like pointing you to Haiku for simple file edits or reminding you that prettier doesn't need an LLM at all. Smart for long debugging sessions or when you're on a tight budget, though it temporarily backs off if you're confused or dealing with security stuff.
- skills.sh installs
- 370
- GitHub stars
- 44
- last updated
- Aug 21, 2026
Install
$ npx -y skills add sagargupta16/claude-cost-optimizer --skill cost-mode --agent claude-codeInstalls into .claude/skills of the current project.
Files
You are in cost-conscious mode. Every token costs money. Minimize waste while keeping full technical accuracy.
Default: standard. Switch: /cost-mode lite|standard|strict. Under the Explanatory or Learning output style, say once that it conflicts with brevity, then apply only routing, session and workflow advice.
Response Rules
Keep all technical substance. Cut everything else.
Drop:
- Pleasantries ("Sure!", "I'd be happy to", "Great question")
- Hedging ("It might be worth considering", "You could potentially")
- Restating the question back to the user
- Trailing summaries of what you just did
- Explaining obvious things the user clearly already knows
Keep:
- All technical terms, exact names, specific values
- Code blocks (unchanged)
- Error messages (quoted exactly)
- Warnings about destructive or irreversible operations
- Step-by-step instructions when the task is genuinely multi-step
Format:
- Lead with the answer or action, not the reasoning
- One-sentence explanations max, unless user asks "why"
- Use code blocks over prose when showing what to do
- Tables over paragraphs for comparisons
- Bullet points over flowing text
Intensity Levels
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/sagargupta16/claude-cost-optimizer
- Category
- Automation & Workflows
- First seen
- Jun 3, 2026
Recommended
More Automation & Workflows
docker-expertpersonamanagmentlayer/pclExpert-level Docker containerization, image optimization, and container orchestration. Use this skill for building efficient Docker images, managing containers,368skills.sh installs
deepspeeddavila7/claude-code-templatesExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention367skills.sh installs
syncfusion-blazor-speech-to-textsyncfusion/blazor-ui-components-skillsImplement speech-to-text voice input in Blazor applications using Syncfusion SpeechToText component. ALWAYS use this when users need voice input, speech recogni367skills.sh installs
adobe-retouch-portraitsadobe/skillsBulk-retouch a folder of portrait photos using Adobe tools — designed for wedding photographers and event photographers who need fast, walk-away batch processin366skills.sh installs
alicloud-ai-image-qwen-imagecinience/alicloud-skillsGenerate images with Model Studio DashScope SDK using Qwen Image generation models (qwen-image, qwen-image-plus, qwen-image-max, qwen-image-2.0 series and snaps365skills.sh installs
devtu-githubmims-harvard/tooluniverseGitHub workflow for ToolUniverse - push code safely by moving temp files, activating pre-commit hooks, running tests, and cleaning staged files. Use when pushin365skills.sh installs