Skip to content

aicraftbook/aicraftbook-skills / skills/cost-compass

cost-compass

Verified

Estimates the monthly running cost of an AI feature, agent or automation from a description of its workload. Breaks the cost into model calls, input, output and cached tokens, and other paid services (search, embeddings, vector database, SMS, voice minutes, automation platform), shows every assumption and the arithmetic, gives a low / expected / high range, and names the two or three changes that would cut the cost most. Uses only prices the user gives or confirms from the provider's pricing page and never invents prices. Use when someone asks "how much will this cost to run", "estimate my API bill", "what will this agent cost per month", "is this automation affordable at 10,000 runs", or wants to compare the running cost of two designs or models.

FileKindSize
CHANGELOG.mdmarkdown1.5 KB
LICENSEother1.0 KB
README.mdmarkdown10.5 KB
SKILL.mdskill md6.6 KB
evals/independent-2026-10-21.jsonconfig60.7 KB
evals/independent-2026-10-22.jsonconfig54.5 KB
evals/results-2026-10-22.jsonconfig5.4 KB
evals/tasks.jsonconfig6.0 KB
examples/requests.mdmarkdown1.3 KB
references/cost-model.mdmarkdown10.0 KB
references/worked-examples.mdmarkdown7.4 KB
skill.jsonconfig2.0 KB

CHANGELOG.md

View on GitHub
# Changelog

## 1.0.2 (2026-10-22)

- Documentation only: README rewritten as a full reference (install per agent, permissions, examples, troubleshooting, test results). SKILL.md and references unchanged.

## 1.0.1 (2026-10-21)

- `references/cost-model.md` §4: Anthropic thinking tokens are described as counted within the billed
  `output_tokens`, with the breakdown field `usage.output_tokens_details.thinking_tokens` (confirmed in
  Anthropic's extended thinking docs).
- §5: OpenAI cache writes stated as its caching guide gives them on 2026-10-21 (GPT-5.6 and later:
  1.25× for the 30-minute lifetime, 2.5× for 12 hours, billed instead of the normal input rate; no
  cache-write charge on earlier models), and the 1,024-token minimum tied to those models.
- `references/worked-examples.md` example 1: at about 8 tickets an hour a 5-minute cache would expire
  between most tickets, so the caching saving now uses the 1-hour cache and its write price
  (new total $44.50, saving $31.29 a month, example prices).
- The evaluations ran on 1.0.0.

## 1.0.0 (2026-10-21)

- First draft. A cost model covering input, output, cached and reasoning tokens, agent history growth,
  batch and other tiers, tool fees, embeddings, retries and non-AI services; three worked examples with
  clearly labelled invented prices; a fixed output format with a low / expected / high range. Price
  structures checked against Anthropic and OpenAI documentation on 2026-10-21. Contains no current prices.
  Not yet evaluated.
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall