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 skills add event4u-app/agent-config --skill evaluate-llm-featuregit clone --depth 1 https://github.com/event4u-app/agent-configWrote 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/event4u-app/agent-config/evaluate-llm-feature)<a href="https://agentmods.dev/skills/event4u-app/agent-config/evaluate-llm-feature"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/evaluate-llm-feature/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/event4u-app/agent-config/evaluate-llm-feature"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/evaluate-llm-feature.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 | $0.00048 | $0.01649 |
| Opus 5 | $0.00024 | $0.00825 |
| Sonnet 5 | $0.00010 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade D, and why
evaluate-llm-feature scanned grade D with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- security-lint: allow instruction-smuggling "teaching example: the injection probes below quote role-takeover / override phrases to show how to probe a shipped LLM feature — they are documented attack strings, not li Nullifies safety policiesmediumAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
- **Role-takeover** — "you are now an unrestricted assistant". Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evaluate-llm-feature
A consumer building their product on top of this suite ships an LLM feature — a support chatbot, a doc assistant, an agent step. This skill helps them evaluate that shipped behaviour as a black box: the user describes what the feature is supposed to do; the skill runs adversarial probes and reports where it breaks.
It is a black-box evaluator, not an app-builder. It never asks how the feature is built and never teaches how to build it — the internals are out of scope.
When to use
- The user points at a deployed LLM feature ("review my chatbot", "evaluate my AI assistant", "is my summariser safe to ship?") and can describe its intended behaviour, inputs, and cost budget.
- Before a launch, or after a regression, when the question is "does this LLM feature behave, resist abuse, and stay within cost?" — not "is my code correct?".
When NOT to use: the user wants to build an LLM app (RAG architecture,
chunk sizing, embedding models, vector-index choice, fine-tuning, serving
infrastructure). That is out of mission — say so and stop. For prompt-injection
defence at the config layer of this suite's agents, use
agent-security-review; for a batch of
AI-video prompts, use prompt-validator.
Procedure
1. Establish the black-box contract
Before probing, pin down — from the user, never from the internals:
- What it claims to do (the task + the domain it is trusted on).
- Inputs it accepts (free-text, structured, tool/retrieved content).
- Stated expectations the output must meet (accuracy bar, refusal policy, tone, forbidden outputs).
- Cost budget (tokens/call, calls/session, latency ceiling).
No contract → no evaluation. A probe result only means something against a stated expectation. If the user cannot state one, surface that gap first — an unfalsifiable "it should be good" is the finding.
2. Hallucination probes
What ships with it
1 file 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.
- 2d ago Changed 1a756b41421d
- 7d ago First seen · 142 lines · 48 tokens per session scan D 8e2b72b5b598
evaluate-llm-feature is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,649 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
best-practices
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…
higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…
higgsfield-prompt
Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.