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/posthog/ai-plugin/exploring-llm-evaluationsnpx skills add PostHog/ai-plugin --skill exploring-llm-evaluationsgit clone --depth 1 https://github.com/PostHog/ai-pluginWrote 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/posthog/ai-plugin/exploring-llm-evaluations)<a href="https://agentmods.dev/skills/posthog/ai-plugin/exploring-llm-evaluations"><img src="https://agentmods.dev/badge/skills/posthog/ai-plugin/exploring-llm-evaluations.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 | $0.00127 | $0.04349 |
| Opus 5 | $0.00063 | $0.02174 |
| Sonnet 5 | $0.00025 | $0.00870 |
| Haiku 4.5 | $0.00013 | $0.00435 |
Grade A, and why
exploring-llm-evaluations 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 405 lines · 127 tokens per session scan A ed1b63bcdd34
exploring-llm-evaluations is a skill published in the GitHub repository PostHog/ai-plugin (80 stars, last pushed yesterday), with no licence file. It adds 127 tokens to every session and 4,349 once invoked, about $0.0006 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
domscribe
Work with Domscribe — the pixel-to-code bridge. Use when setting up, initializing, or configuring Domscribe for a project, OR when editing or modifying UI components (React, Vue, Next.js, Nuxt), implementing features from captured UI annotations, querying runtime context for source locations, exploring component…
proctor
Honest-completion ruleset for changes that touch tests or the code they cover. Use before deleting, skipping, renaming, or rewriting a test, before weakening an assertion, and before hardcoding or stubbing an implementation to make a test pass. Also covers what to do when a test looks genuinely wrong.
wavedash
Use when building, integrating, testing, uploading, publishing, or preparing a browser game for Wavedash, including CLI setup, Wavedash SDK features, multiplayer, achievements, leaderboards, cloud saves, player identity, user-generated content, store metadata, monetization, and content guidelines.
motherduck-build-cfa-app
Design a MotherDuck-backed customer-facing analytics app. Use for embedded analytics, multi-tenant SaaS reporting, or product analytics for external users -- whenever the decision depends on per-customer isolation, backend routing, service-account boundaries, read scaling, or Hypertenancy-style patterns.
motherduck-build-dashboard
Build a live MotherDuck dashboard as a Dive. Use when composing one shareable KPI, trend, and breakdown story over existing MotherDuck data, especially when the result should stay a saved workspace artifact rather than a full application.
motherduck-build-data-pipeline
Design an end-to-end MotherDuck data pipeline. Use for ETL/ELT workflows -- choosing raw, staging, and analytics boundaries, bulk ingestion paths, transformation sequencing, dlt/dbt integration, publication targets, or whether DuckLake is actually required.