agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/LifeSciences/applications/foldrun/foldrun-agent/foldrun_app/skills/packages/cost-estimation/SKILL.md

cost-estimation

Skill53 starsChanged 55 days agoApache-2.0View on GitHub

Job cost forecasting, on-demand vs DWS spot pricing comparison, and spending analysis

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Per-job cost: Use estimate_job_cost to show users the expected cost before submitting a prediction

    line 13
  2. Very specific:

    IMPORTANT: Always present both pricing columns so users can compare.

    line 17
  3. Distinctive:

    Proactive use: When showing the pre-submission confirmation table, include cost estimate

    line 18
  4. Distinctive:

    Monthly projection: Use estimate_monthly_cost for budget planning and TCO analysis

    line 19
  5. Distinctive:

    Use include_infrastructure=False to see compute-only costs

    line 23
  6. Distinctive:

    Actual costs: Use get_actual_job_costs to retrieve costs for completed prediction jobs

    line 24
  7. Distinctive:

    Use this when users ask "how much did that job cost?" or "show me my spending"

    line 29

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Cost Estimation

  • Per-job cost: Use estimate_job_cost to show users the expected cost before submitting a prediction
    • Supports AF2 monomer, AF2 multimer, and OF3 job types
    • Returns per-phase breakdown (MSA, predict, relax) with both on-demand and DWS FLEX_START (spot) pricing side by side
    • GPU auto-selection matches the submission tools (L4 for small proteins, A100 for larger)
    • IMPORTANT: Always present both pricing columns so users can compare. FoldRun defaults to FLEX_START.
    • Proactive use: When showing the pre-submission confirmation table, include cost estimate
  • Monthly projection: Use estimate_monthly_cost for budget planning and TCO analysis
    • Input monthly job volumes by type (AF2 monomer, multimer, OF3)
    • Returns compute + infrastructure + other costs with monthly and annual totals for both pricing modes
    • Infrastructure includes: Filestore, GCS, Artifact Registry, Agent Runtime, Cloud Run, VPC/NAT
    • Use include_infrastructure=False to see compute-only costs
  • Actual costs: Use get_actual_job_costs to retrieve costs for completed prediction jobs
    • Calculates costs from actual Agent Platform job runtimes and machine specs
    • Groups costs by pipeline run with per-phase breakdown (MSA, predict, relax)
    • Shows estimate vs actual comparison with accuracy percentage
    • Provide a pipeline_job_id for a specific run, or omit to see all recent jobs
    • Use this when users ask "how much did that job cost?" or "show me my spending"
  • IMPORTANT disclaimer: These tools return estimates based on Google Cloud list pricing. Always remind users that actual costs depend on their organization's pricing agreement with Google Cloud (negotiated rates, CUDs, enterprise discounts). The disclaimer is included in every tool response — surface it to the user.

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