luum-home/luum-cognitive-os/cost-predictor
- community
Checking that the SKILL.md file is still in the repository.
'Use when you need this Cognitive OS skill: Predict task cost from Cognitive
Install
npx vskill@latest install luum-home/luum-cognitive-os/cost-predictorSKILL.md
Cost Predict
Purpose
Give a real, bounded cost estimate before starting medium+ work. This skill uses the existing lib/cost_predictor.py engine and the metrics already written by Cognitive OS, so the output is grounded in project history rather than a generic guess.
Invoke
When to Use
- Before starting a medium, large, or critical task
- When deciding whether to split work into smaller slices
- When comparing implementation strategies with different likely costs
- When you need a budget forecast tied to real repository history
Steps
Step 1: Classify the task
Read the task description and choose the closest task_type:
featurebugfixrefactordocsresearch
If the task spans multiple types, choose the dominant cost driver and say so explicitly.
Step 2: Run the predictor
Use the executable wrapper:
If you need structured output for follow-on automation, use:
Step 3: Read the evidence
Interpret the result in this order:
- Estimated range (
min,mid,max) - Confidence level
- Basis (
historical,model_routing,no_data) - Similar tasks, if present
- Recommendation
If the basis is no_data or confidence is low, say that clearly and treat the output as a planning hint, not a commitment.
Step 4: Turn the estimate into a decision
- If cost is low and confidence is decent, proceed normally
- If cost is moderate or high, propose splitting the work
- If confidence is low, recommend a smaller exploratory slice first
- If the estimate is driven mostly by expensive phases, call that out
Output Format
Contextual Trigger
Use this skill when the user asks how much a task will cost, asks for a budget forecast, or needs a quick estimate before implementation.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/cost-predictor/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/luum-home/luum-cognitive-os/cost-predictor)