You don’t know what will break first or what growth will cost.
See the next bottleneck and estimate the cost before it becomes an incident.
- CPU, memory, disk
- database limits
- file storage
- API spend
- growth risks
Tell your agent
npx skills add bookops/skillscheck capacity and cost with akukikiInstalls into Claude Code, Codex, Cursor, OpenCode, Gemini CLI, OpenClaw, Hermes and other agents; tested in Claude Code and OpenCode. The audit takes a few minutes. Your agent reads the project and changes or sends nothing without your explicit yes.
What akukiki checks
- How much CPU, memory and disk is left on the server?
- Will the database cope with more users at once?
- Are there queries that read whole tables?
- Are slow jobs done outside the web request?
- Are sign-in and expensive endpoints rate-limited?
- Where do uploaded files live?
- Do paid APIs have limits and a spending cap?
- What will it cost at 100, 1,000 and 10,000 users?
Example report
Disk — 87% full, mostly uploads and logs
Rate limits — sign-in can be tried without limit
Database — one SQLite file for every write
Cost — no estimate for more users
Paid APIs — none used
You stay in control.
- Your agent reads the project, sees only what it can already reach and changes nothing without your yes. The skill never asks for passwords or keys.
- Your code, files and secrets stay with you. A short summary reaches akukiki only after your explicit yes — your agent shows it to you first.
- “Read-only” and “fixes only after your yes” are rules in the skill’s instructions, not a sandbox. You can read the skill file before you run it.
For AI agents
This skill is a SKILL.md file. It reads the project, prints a report and, only with the user’s explicit consent, sends a short summary to akukiki and makes simple fixes in the project.
Claude Code can also take it as a plugin that updates itself: /plugin marketplace add bookops/skills, then /plugin install akukiki@bookops.
Hermes: hermes skills install well-known:https://akukiki.com/.well-known/skills/akukiki