agentleFS
Sign inStart free
dRafaleDdRafaleD/cybersec-skills/skills/infrastructure/lean-cost/SKILL.md

lean-cost

Skill2 starsChanged 57 days agoMITView on GitHub

Runs token-efficient cloud and CI cost reviews for Cursor and Codex. Inventories always-on compute, unpinned latest images, large artifacts, and chatty logging in local IaC and workflows, then reports compact spend cuts. Use when the user asks for cloud cost, token waste, CI minutes, or cheaper infrastructure. Do not use for attacking billing APIs or other accounts.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run spend. Queue instance_type large, count high, latest images, artifacts always uploaded, debug logging on.

    line 38
  2. Very specific:

    If they paste a cost CSV, trim it.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lean Cost

Spend cuts from local Terraform, compose, and workflows. No live billing scrape unless the user already exported a CSV.

Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.

python3 "$SKILL_ROOT/scripts/lean_cost.py" spend .
python3 "$SKILL_ROOT/scripts/lean_cost.py" trim --chars 2500 path/to/out.txt

Mode

Default lean.

ModeBudget
leanspend + up to 8 slices; references/waste.md; ≤6 findings
standardup to 16 slices; ≤10 findings
deepstill no invoice dump; ≤16 findings

Workflow

  1. Run spend. Queue instance_type large, count high, latest images, artifacts always uploaded, debug logging on.
  2. Slice-read. Cap quotes at 12 lines.
  3. Report smaller size, schedule, or drop. Stop unless asked to patch.

Hard rules

  • This workspace's config. Do not query another tenant's billing.
  • If they paste a cost CSV, trim it; do not keep the whole file in context.

Report template

## Lean-cost (`<mode>`)

**Stack:** <tf/compose/ci> | **Budget:** files_read=<n>

| Sev | Location | Issue | Fix |
|-----|----------|-------|-----|
| MED | file:line | always-on large instance | smaller type or stop schedule |

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free