pricing-check

pricing-check is a command for coding agents from omrikais/cctally. It costs 0 tokens per session (2,627 once invoked), scanned A, original, Apache-2.0.

A check for missing or outdated model prices in cctally’s local pricing tables. It compares saved session models with the prices cctally uses to calculate costs.

In plain words
What is it for?
Use it to check pricing coverage across saved sessions, detect changes against LiteLLM’s model data, and run a weekly pricing check in continuous integration (automated project checks).
Why use it?
It helps prevent reports from showing Claude usage as $0 or estimating Codex usage with the wrong fallback price. This exposes pricing gaps before someone has to find them manually.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/omrikais/cctally/pricing-check
Clone the repo
git clone --depth 1 https://github.com/omrikais/cctally

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 pricing-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/omrikais/cctally/pricing-check.svg)](https://agentmods.dev/commands/omrikais/cctally/pricing-check)
Your own site
<a href="https://agentmods.dev/commands/omrikais/cctally/pricing-check"><img src="https://agentmods.dev/badge/commands/omrikais/cctally/pricing-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02627
Opus 5 $0.00000 $0.01314
Sonnet 5 $0.00000 $0.00525
Haiku 4.5 $0.00000 $0.00263

Measured 4d ago against content hash 6be56953da9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pricing-check scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/pricing-check.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pricing-check

Detect whether cctally's embedded model pricing (CLAUDE_MODEL_PRICING / CODEX_MODEL_PRICING) has gone stale or is missing a model. cctally prices every session locally from these embedded tables; an unrecognized Claude model silently contributes $0 and an unrecognized Codex model is approximated via the gpt-5 fallback. This command surfaces those gaps proactively instead of waiting for someone to reconcile by hand.

It is the network-aware counterpart to the offline doctor pricing.coverage check, and the entry point for the weekly pricing-freshness CI workflow.

Synopsis

cctally pricing-check [--json] [--offline]

Purpose

Three independently-degrading legs:

  1. Coverage (offline, all-history) — models in your cached session data (cache.db) that cctally cannot price exactly: Claude models priced at $0 (unpriced) or Codex models approximated via the gpt-5 fallback (fallback). The Codex ingest sentinel unknown is excluded: it means the rollout did not retain a model identifier, so it is not a model that can be added to the pricing table. No network; a read-only scan over the cache.
  2. Drift (network, LiteLLM) — embedded price values vs the LiteLLM pricing snapshot. Direction-aware (see below) and allowlist-suppressed.
  3. Existence (network, Anthropic /v1/models) — vendor models the API offers that our table lacks. Anthropic-only and maintainer-local (needs a Claude OAuth bearer); see the asymmetry + caveat sections.

The tool detects; a human applies. It never auto-edits the pricing tables — the verified-against-vendor discipline stays.

Options

Flag Effect
--json Emit the machine-readable payload (schemaVersion: 1) to stdout. CI consumes this.
--offline Run the coverage leg only. The drift + existence legs are skipped (no network).

Exit codes

Exit code and status are orthogonal: the exit code reports whether you must act; status reports whether the check was complete.

Read the full file on GitHub · 208 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. 4d ago First seen · 208 lines · 0 tokens per session scan A 6be56953da9e

Subscribe to this mod's changes

pricing-check is a command published in the GitHub repository omrikais/cctally (5 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,627 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.