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.
npx agentmods add skills/agentconnect-md/agentconnect/update-model-pricingnpx skills add agentconnect-md/agentconnect --skill update-model-pricinggit clone --depth 1 https://github.com/agentconnect-md/agentconnectWrote 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/agentconnect-md/agentconnect/update-model-pricing)<a href="https://agentmods.dev/skills/agentconnect-md/agentconnect/update-model-pricing"><img src="https://agentmods.dev/badge/skills/agentconnect-md/agentconnect/update-model-pricing.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.00699 |
| Opus 5 | $0.00039 | $0.00349 |
| Sonnet 5 | $0.00016 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Model Pricing
Keep the daemon's offline cost fallback aligned with current public OpenAI Standard API pricing and the codex-acp version selected by AgentConnect's runtime registry or an explicit runtime override.
Workflow
- Read
packages/daemon/src/usage/openai-public-pricing.ts, its focused test, andpackages/daemon/src/runtimes/registry.ts. Resolve the effective codex-acp package/version from the current ACP registry entry or the deployment's explicit runtime command/args; it is not pinned inpnpm-lock.yaml. - Read references/pricing-sources.md and fetch the current official sources. Do not rely on remembered prices or third-party tables.
- Re-check the resolved codex-acp tag's
TokenCountmapping and compare it with upstream main before changing the formula. Confirm whether ACP input, cache-read, cache-write, output, and thought fields are disjoint and whether PromptResponse usage is per-turn. - Update the manifest with exact published model IDs, prices, dated snapshots, thresholds, and the verification date. Cover text/reasoning models that codex-acp advertises or AgentConnect explicitly supports; do not broaden the manifest to unrelated OpenAI products. Keep unknown models unsupported; never infer a price by prefix or strip an unlisted date suffix.
- Update tests in the same patch. Cover every alias, the exact long-context boundary, cache behavior, unknown models, malformed usage, and reasoning non-duplication.
- Run the focused daemon tests, daemon typecheck, and formatting check. Review the final diff for unrelated product or telemetry changes.
Repository Rules
- Price Standard API tokens in USD per one million tokens. Do not branch on ChatGPT subscription versus API-key authentication.
- Prefer an ACP-provided cost for a turn. Run fallback calculation only when that turn reports no cost.
- Keep cost display unchanged. Do not add estimated labels, approximation glyphs, or CP/Web schema fields unless explicitly requested.
- Calculate each Codex turn with the model selected for that session at turn start; do not reprice a whole session using its final model.
- Treat output tokens as already including reasoning tokens. Never add thought tokens a second time.
- Apply a long-context tier only when the public table publishes one and request input is strictly above its documented threshold.
- Keep runtime pricing offline and deterministic. Never fetch prices from the daemon at runtime.
- Preserve historical stored amounts; a price refresh affects only future fallback turns.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 41 lines · 79 tokens per session scan A ea290671622a
update-model-pricing is a skill published in the GitHub repository agentconnect-md/agentconnect (868 stars, last pushed 5d ago), licensed Apache-2.0. It adds 79 tokens to every session and 699 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
risk-scoring
Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.
valuation
Estimate whether a stock looks cheap or expensive using a price-to-earnings (P/E) based fair-value method. Use when the user asks if a stock is over- or under-valued, or for a fair-value / target price.
opentag
Use when installing, pairing, operating, or troubleshooting OpenTag through the published CLI, self-hosted Control Plane, governed completion, supported collaboration platforms, or built-in coding agents.
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
vertical-fintech-mobile
Domain-knowledge pack for money on a phone — wallets, payments, custody and signing, transaction lifecycle, KYC/AML gates, and offline reconciliation. The rules that separate a payments app from a CRUD app with a currency symbol: a balance is a claim about a server, an idempotency key must outlive the process that…
augur-lynch
Peter Lynch AI — GARP / PEG, consumer growth, everyday observations.