Borrowing it
Nothing to install: this file belongs to dosu-ai/decant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dosu-ai/decant/main/.claude/skills/update-model-pricing/SKILL.mdgit clone --depth 1 https://github.com/dosu-ai/decantWrote 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.
[](https://agentmods.dev/skills/dosu-ai/decant/update-model-pricing)<a href="https://agentmods.dev/skills/dosu-ai/decant/update-model-pricing"><img src="https://agentmods.dev/badge/skills/dosu-ai/decant/update-model-pricing/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.
<a href="https://agentmods.dev/skills/dosu-ai/decant/update-model-pricing"><img src="https://agentmods.dev/badge/skills/dosu-ai/decant/update-model-pricing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00399 |
| Opus 5.5 | $0.00021 | $0.00160 |
| Sonnet 5.5 | $0.00010 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
update-model-pricing 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 28d 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.
What it actually says
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
- Verify every rate against the provider's first-party pricing page. Do not use third-party aggregators or memory.
- 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. - Update
docs/pricing.md: the table row, the source link list, and the dated "verified on" sentence at the top. - Add cases to
test/cost.test.tsfor each new or changed pattern, including dated-suffix variants of the model ID. - 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.
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.
- 28d ago First seen · 42 lines · 52 tokens per session scan A eb7963ff482d
update-model-pricing is a skill published in the GitHub repository dosu-ai/decant (72 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 399 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
aitask-run-gates
Run a task's declared gates — the conversational front of the headless gate orchestrator engine. Dispatches unlocked machine-gate verifiers within their retry budgets, observes human gates without self-signalling, and reports.
aitask-add-model
Register a known code-agent model in models .json, optionally promote it to default across config/seed/DEFAULTAGENTSTRING.
money
Skill "money" from Hmbown/Codewhale, covering money, when to use, setup, workflow and non-goals.
cdf-anomalygen
Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…