cost-estimator

Featured

Pre-flight cost estimate for a planned /article run. Use BEFORE /article or when user asks "how much will this cost?" / "what's the estimate?". Outputs USD breakdown by category + 80% confidence band + budget check.

AI & Automation 43 stars 13 forks Updated 3 days ago Apache-2.0

Install

View on GitHub

Quality Score: 89/100

Stars 20%
55
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Cost Estimator (Pre-flight) Before user commits 30 min + $2.40 to /article, show them the estimate. ## When to invoke - `/cost-estimate` — defaults to listicle 6000w - `/cost-estimate listicle 6000` - `/cost-estimate --brief workspace/abc/brief.json` - User asks: "how much for a pillar page?", "what does an article cost?", "is this gonna be over budget?" - Auto-trigger via L1 SKILL.md before phase-research starts (mandatory pre-flight) ## How to invoke ```bash # By format + word count python -m scripts._core.cost_estimator --format listicle --words 6000 # From an existing brief.json python -m scripts._core.cost_estimator --brief workspace/abc123/brief.json --json # With cheaper config python -m scripts._core.cost_estimator \ --format how-to-guide --words 4500 \ --images 2 --image-quality medium --batch # Machine-readable python -m scripts._core.cost_estimator --format pillar-page --json ``` ## Output (human-readable) ``` ━━━ /article cost estimate ━━━━━━━━━━━━━━━━━━━━━━━━━ Format: listicle (target 6000 words) Images: 4 × high-quality 1024² (batch) Drafter / pipeline model: claude-opus-4-7 / claude-opus-4-7 Cache hit rate assumed: 30% Breakdown: Research (Tavily ×8 adv search + 12 extracts): $0.1664 Drafting (6000w via claude-opus-4-7, 21,000 in + 8,400 out + 9,000 cached): $0.3360 Pipeline stages (13 stages, 124,000 in + 13,500 out via claude-opus-4-7): $0.6469 Images (4 × gpt-image-2 high 1024² batch): $0.4220 Overhead buffer (10%): $0....

Details

Author
XuanRanL
Repository
XuanRanL/loamwright-SEO-Skill
Created
2 weeks ago
Last Updated
3 days ago
Language
Python
License
Apache-2.0

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

cost-estimation

Use when the user wants to estimate or predict the cost, token usage, or time of a task BEFORE it runs — "how much will this feature cost to build", "estimate the tokens for this spec", "what will this slice cost", "predict the agent-compute time before I commit" — produces a token + time estimate as a range with disclosed confidence, adding a dollar figure only when an observability/costs snapshot grounds it. The prospective sibling of cost-tracking, which records actual spend after the fact.

45 Updated 6 days ago
Habitat-Thinking
AI & Automation Listed

cost_estimator

Estimate what a task or a fix will cost — tokens, model/tier, money ($), and wall-time — using the tiered cost model. Use whenever the user wants to know the cost of a correction, audit, or task before running it, or to compare local vs cloud cost.

1 Updated yesterday
zedarvates
AI & Automation Listed

token-cost-estimator

Use this skill before running any prompt in production or sharing a workflow with stakeholders. Triggers on phrases like "how much will this cost", "compare model costs", "which model should I use", "estimate tokens", "pre-flight check", or when a user pastes a prompt and asks about inference economics. Takes a prompt and a list of candidate models, then returns a projected cost and latency comparison across all models before a single token runs. Essential for any AI PM who owns inference budgets. Do NOT use as a substitute for current provider pricing or measured production latency.

1 Updated 1 months ago
Abhillashjadhav