fluxion-bus: Skill for Claude Code

.agents/skills/update-model-prices/SKILL.md

update-model-prices is a skill for Claude Code, Codex from superposed-labs/fluxion-bus. It costs 172 tokens per session (3,269 once invoked), scanned A, original, Apache-2.0.

A procedure for updating the model price data used by Fluxion, a tool that estimates the dollar cost of AI token usage. It refreshes the upstream price table and Fluxion’s bundled copy using official provider pricing pages.

In plain words
What is it for?
Use it when refreshing prices for Anthropic, OpenAI, or Google Gemini models and preparing the corresponding updates in both repositories.
Why use it?
AI model prices change, and Fluxion has no official pricing API, so its estimates can become outdated without a deliberate review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Claude Code; installed under .agents/ (shared by several agents).

This is superposed-labs/fluxion-bus's own configuration. It tells Claude Code and Codex how to work on fluxion-bus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fluxion-bus configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/update_model_prices.py --offline.

Reuse

Borrowing it

Nothing to install: this file belongs to superposed-labs/fluxion-bus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/superposed-labs/fluxion-bus/main/.agents/skills/update-model-prices/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/superposed-labs/fluxion-bus

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for update-model-prices

README.md
[![agentmods](https://agentmods.dev/badge/skills/superposed-labs/fluxion-bus/update-model-prices/github.svg)](https://agentmods.dev/skills/superposed-labs/fluxion-bus/update-model-prices)
Your own site
<a href="https://agentmods.dev/skills/superposed-labs/fluxion-bus/update-model-prices"><img src="https://agentmods.dev/badge/skills/superposed-labs/fluxion-bus/update-model-prices/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-model-prices

Your own site · 80×15
<a href="https://agentmods.dev/skills/superposed-labs/fluxion-bus/update-model-prices"><img src="https://agentmods.dev/badge/skills/superposed-labs/fluxion-bus/update-model-prices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00172 $0.03269
Opus 5 $0.00086 $0.01635
Sonnet 5 $0.00034 $0.00654
Haiku 4.5 $0.00017 $0.00327

Measured 10d ago against content hash 9709cf6b8444, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

update-model-prices scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Google serve prices in plain HTML, so `curl`/WebFetch is enough for those.
.agents/skills/update-model-prices/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update model prices

Fluxion estimates the dollar cost of token usage from a hand-maintained price table. There is no official pricing API, and the CLIs run models newer than any public price list, so prices are refreshed by a person running this procedure on demand (a few times a year, when prices change) — not by a scheduled scraper.

Your job here is the judgment-heavy part a cron can't do: render the pages, read the numbers semantically, decide how each model maps into the table, and hand the human a clear, correct proposal. The mechanical fetching/auditing is already scripted.

Where the table lives — edit upstream first

The source of truth is the standalone repo superposed-labs/llm-price-table (its SCHEMA.md defines the format). src/fluxion/usage/model_prices.json is a bundled snapshot of that file — the offline fallback and release baseline. At runtime price_data.load_price_json picks whichever of the snapshot and the locally refreshed cache carries the newer top-level updated_at, so the daily background refresh normally delivers a new price within a day even with no Fluxion change at all.

A price change therefore lands in two repos, in this order:

  1. Edit model_prices.json in the llm-price-table checkout; bump its updated_at.
  2. Copy that file verbatim over src/fluxion/usage/model_prices.json.

Keep the snapshot a byte-for-byte copy and diff the two afterwards. Drift is a silent bug: a family present upstream but missing from the snapshot mispriced every id that resolved through it (this actually happened with mythos, which fell through to the coarse claude fallback at half the real rate).

The one hard rule

Propose, never auto-apply. A wrong number silently corrupts every cost figure in the dashboard, so a human must verify before anything lands. Produce a clear summary of proposed changes and stop. Only edit the file if the user explicitly approves the specific numbers, and never git commit — committing is always the user's call. Git history is the price-change log, so it must stay human-authored.

Read the full file on GitHub · 244 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 244 lines · 172 tokens per session scan A 9709cf6b8444

Subscribe to this mod's changes

update-model-prices is a skill published in the GitHub repository superposed-labs/fluxion-bus (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 172 tokens to every session and 3,269 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.