Agent skill
cost-optimizer
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.
Install this agent skill to your Project
npx add-skill https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/cost-optimizer
Metadata
Additional technical details for this skill
- tags
-
cost optimizer cost-budget too-expensive reduce-cost
- pairs with
-
[ { "skill": "cost-accrual-tracker", "reason": "The tracker provides the real-time cost data that the optimizer uses for budget decisions" }, { "skill": "llm-router", "reason": "Model routing is the primary mechanism through which cost optimization is enacted" }, { "skill": "cost-verification-auditor", "reason": "Post-execution auditing validates that optimization decisions actually reduced costs" } ]
SKILL.md
Cost Optimizer
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget: downgrade models, skip optional nodes, or stop early.
When to Use
✅ Use for:
- Setting and enforcing cost budgets for DAG executions
- Real-time cost monitoring during execution
- Deciding when to downgrade model tiers mid-execution
- Identifying which nodes are most expensive and why
- Post-execution cost analysis and optimization recommendations
❌ NOT for:
- Choosing which model to use per node (use
llm-router) - Provider pricing comparisons (static data, not a skill)
- Billing or invoicing features
Budget Enforcement Process
flowchart TD
N[Node about to execute] --> C[Check: spent + estimated_node_cost vs budget]
C --> S{Within budget?}
S -->|Yes, >20% remaining| E[Execute at planned model tier]
S -->|Yes, <20% remaining| W[Execute but downgrade to Tier 1 if possible]
S -->|No| D{Node optional?}
D -->|Yes| SK[Skip node]
D -->|No| H{Human gate available?}
H -->|Yes| A[Ask human: continue over budget?]
H -->|No| ST[Stop execution, return partial results]
Budget Tiers
| Budget Remaining | Action |
|---|---|
| >50% | Execute at planned model tier |
| 20-50% | Log warning. Continue at planned tier. |
| 10-20% | Downgrade remaining Tier 2 nodes to Tier 1 (Haiku) |
| 5-10% | Downgrade ALL remaining nodes to Tier 1. Skip optional nodes. |
| <5% | Stop execution unless next node is critical path |
| 0% | Stop. Return partial results with cost breakdown. |
Cost Estimation Per Node
Before each node executes, estimate its cost:
estimated_cost = (avg_input_tokens × input_price + avg_output_tokens × output_price)
Use historical averages for this skill + model combination. If no history, use defaults:
- Tier 1 (Haiku): ~800 input + 400 output = ~$0.001
- Tier 2 (Sonnet): ~2000 input + 1000 output = ~$0.012
- Tier 3 (Opus): ~3000 input + 1500 output = ~$0.16
Post-Execution Report
cost_report:
total_budget: 0.50
total_spent: 0.37
budget_remaining: 0.13
nodes_executed: 8
nodes_skipped: 1
nodes_downgraded: 2
model_breakdown:
haiku: { calls: 4, cost: 0.004 }
sonnet: { calls: 3, cost: 0.036 }
opus: { calls: 1, cost: 0.33 }
savings_recommendations:
- "Node 'deep-analysis' used Opus ($0.33) but downstream accepted on first try. Try Sonnet next time — potential saving: $0.32"
- "Nodes 'validate-a' and 'validate-b' are sequential but independent. Parallelize to reduce wall-clock time."
Anti-Patterns
No Budget at All
Wrong: Running DAGs without any cost tracking until the API bill arrives. Right: Every DAG execution has a budget, even if generous. Track spend per node.
Aggressive Downgrading
Wrong: Downgrading Opus nodes to Haiku at 50% budget remaining, causing quality failures that trigger expensive retries. Right: Only downgrade when the alternative is stopping execution. Retries cost more than the original model tier.
Ignoring Retries in Cost
Wrong: Budgeting for one attempt per node. Right: Budget for avg_retries × cost_per_attempt. A node with 3 retries on Sonnet costs $0.036, not $0.012.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
curiositech/some_claude_skills
3d-cv-labeling-2026
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
curiositech/some_claude_skills
project-management-guru-adhd
Expert project manager for ADHD engineers managing multiple concurrent projects. Specializes in hyperfocus management, context-switching minimization, and parakeet-style gentle reminders. Activate on 'ADHD project management', 'context switching', 'hyperfocus', 'task prioritization', 'multiple projects', 'productivity for ADHD', 'task chunking', 'deadline management'. NOT for neurotypical project management, rigid waterfall processes, or general productivity advice without ADHD context.
curiositech/some_claude_skills
large-scale-map-visualization
Master of high-performance web map implementations handling 5,000-100,000+ geographic data points. Specializes in Leaflet.js optimization, Supercluster algorithms, viewport-based loading, canvas rendering, and progressive disclosure UX patterns.
curiositech/some_claude_skills
adhd-design-expert
Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.
curiositech/some_claude_skills
liaison
Translate multi-agent ecosystem activity into human-readable status briefings, decision requests, and progress summaries. Use for 'status update', 'brief me', 'what happened', 'summarize progress'. NOT for project planning (use project-management-guru-adhd), code review, or technical documentation.
curiositech/some_claude_skills
windows-95-web-designer
Modern web applications with authentic Windows 95 aesthetic. Gradient title bars, Start menu paradigm, taskbar patterns, 3D beveled chrome. Extrapolates Win95 to AI chatbots, mobile UIs, responsive layouts. Activate on 'windows 95', 'win95', 'start menu', 'taskbar', 'retro desktop', '95 aesthetic', 'clippy'. NOT for Windows 3.1 (use windows-3-1-web-designer), vaporwave/synthwave, macOS, flat design.
Didn't find tool you were looking for?