agentleFS
Sign inStart free
dosu-aidosu-ai/decant/.claude/skills/update-model-pricing/SKILL.md

update-model-pricing

Skill74 starsChanged 9 days agoApache-2.0View on GitHub

Add or change model token rates in Decant. Use when a provider publishes new pricing, a new model needs a rate, a model ID pattern fails to match, or a retired model should stop inheriting a current tier's price.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. agentconnect-md/agentconnect★ 1.5ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify every rate against the provider's first-party pricing page.

    line 13
  2. Very specific:

    Update docs/pricing.md: the table row, the source link list, and the dated "verified on" sentence at the top.

    line 18
  3. Very specific:

    Add cases to test/cost.test.ts for each new or changed pattern, including dated-suffix variants of the model ID.

    line 20
  4. Very specific:

    If context-window sizes changed too, update the model window tests in test/context-window.test.ts.

    line 22
  5. Distinctive:

    Every sync reprices stored session and activity costs with current rates, so a rate change needs no migration.

    line 27

≈ “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

Update model pricing

Rates live in src/cost.ts and are documented in docs/pricing.md. AGENTS.md invariant 4 explains why stored costs follow current rates.

Steps

  1. Verify every rate against the provider's first-party pricing page. Do not use third-party aggregators or memory.
  2. Edit the pricing table and model-ID patterns in src/cost.ts. Retired models without a published rate stay unpriced rather than falling through to a newer tier.
  3. Update docs/pricing.md: the table row, the source link list, and the dated "verified on" sentence at the top.
  4. Add cases to test/cost.test.ts for each new or changed pattern, including dated-suffix variants of the model ID.
  5. If context-window sizes changed too, update the model window tests in test/context-window.test.ts.

What happens to existing archives

Every sync reprices stored session and activity costs with current rates, so a rate change needs no migration. Bump INGEST_PIPELINE_REVISION only when unchanged sources must be re-derived, for example when session model selection changes which model a session is attributed to.

Goldens

Golden outputs that include cost change when a fixture model's rate changes. Review that diff line by line, then regenerate with bun run scripts/regen-goldens.ts --i-reviewed-the-diff.

Prior art

git log --oneline -- src/cost.ts docs/pricing.md shows earlier pricing changes and the tests that shipped with them.

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