Borrowing it
Nothing to install: this file belongs to Nayjest/ai-microcore. 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/Nayjest/ai-microcore/main/.github/prompts/check-model-presets.mdgit clone --depth 1 https://github.com/Nayjest/ai-microcoreWrote 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/commands/nayjest/ai-microcore/check-model-presets)<a href="https://agentmods.dev/commands/nayjest/ai-microcore/check-model-presets"><img src="https://agentmods.dev/badge/commands/nayjest/ai-microcore/check-model-presets/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/commands/nayjest/ai-microcore/check-model-presets"><img src="https://agentmods.dev/badge/commands/nayjest/ai-microcore/check-model-presets.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 | $0.00000 | $0.01410 |
| Opus 5.5 | $0.00000 | $0.00564 |
| Sonnet 5.5 | $0.00000 | $0.00282 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
check-model-presets 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check provider model presets
Compare the provider model presets with the models the vendors currently offer. You run inside
the Check model presets workflow and don't edit project files. Instead, you write one result
file (see Output): proposal.md when something is outdated, or up-to-date.md when nothing is.
The workflow files a proposal as a GitHub issue, and another workflow implements that issue
without web access, so a proposal must contain everything the implementation needs.
Models released after your training cutoff are real. Take model IDs and prices from the vendors' current official documentation, never from memory.
What to check
- Presets in
microcore/llm_backends.py:HIGH_END_MODELS,MID_END_MODELSandLOW_END_MODELS. Check every platform listed there.- Each entry carries its standard list price as
# I/O: $<input>/$<output> /M tokens, using the base rate (no batch, cache or long-context pricing), with a short qualifier where the vendor has more than one rate, as in(peak). Propose fixes for stale prices on unchanged entries too. - Don't propose new platforms or new preset tiers. You may propose adding a
MID_END_MODELSentry for a platform whose vendor has an obvious mid-tier model.
- Each entry carries its standard list price as
- Docs and examples that name current models and must stay consistent with the presets:
- the model lists in
.env.*.examplefiles - model examples in
README.md, such asllm('1+2=', model=...) examples/ask_various_llms_via_mcp/: bothREADME.mdandask_various_llms_mcp_server.py(keys use dotted versions such as"claude-opus-5.5",modeluses the exact API ID)
- the model lists in
- Leave statements about specific older models alone when they describe that model's behavior
rather than a current default (for example "GPT-5.6 with function tools requires the Responses
API"). Leave test fixtures alone unless a test asserts a preset value. Leave
.github/and the package version alone; the workflow adds the version change.
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.
- 2d ago First seen · 106 lines · 0 tokens per session scan A c92e3209b9c3
check-model-presets is a command published in the GitHub repository Nayjest/ai-microcore (108 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,410 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 2026-10-19.
Other commands, from other repositories
xp-finish
Finish the active XP session using the real backend.
framework-builder
Run the real Limitless framework builder for a topic.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.