mcp-cs: Skill for Claude Code

.agents/skills/ai-prompt-evaluator/SKILL.md

ai-prompt-evaluator is a skill for Claude Code, Codex from ieeecsopen/mcp-cs. It costs 109 tokens per session (662 once invoked), scanned B, original, no licence file.

A tool for designing, testing, and improving instructions for language models and agents, including their required JSON output formats and defenses against malicious instructions.

In plain words
What is it for?
Use it to evaluate or red-team system prompts, agent instructions, structured JSON schemas, and protections against prompt injection and hallucinations.
Why use it?
It helps find weaknesses in prompts and agent rules that could cause incorrect output, unsafe behavior, or prompt-injection failures.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is ieeecsopen/mcp-cs's own configuration. It tells Claude Code and Codex how to work on mcp-cs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-cs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ieeecsopen/mcp-cs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ieeecsopen/mcp-cs/main/.agents/skills/ai-prompt-evaluator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ieeecsopen/mcp-cs

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ai-prompt-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator/github.svg)](https://agentmods.dev/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator)
Your own site
<a href="https://agentmods.dev/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator"><img src="https://agentmods.dev/badge/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator/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.

agentmods 80×15 button for ai-prompt-evaluator

Your own site · 80×15
<a href="https://agentmods.dev/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator"><img src="https://agentmods.dev/badge/skills/ieeecsopen/mcp-cs/ai-prompt-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.00662
Opus 5 $0.00055 $0.00331
Sonnet 5 $0.00022 $0.00132
Haiku 4.5 $0.00011 $0.00066

Measured 11d ago against content hash fe0fa957001a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

ai-prompt-evaluator scanned grade B 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 11d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

Design robust, deterministic, and injection-resistant system prompts for AI agents and LLM applications. Poorly structured prompts suffer from instruction drift, role confusion, hallucinations under ambiguous inputs, and

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

description: Activate when designing, evaluating, red-teaming, and refining LLM system prompts, agent instructions, structured JSON schemas, and defense boundaries against prompt injections and hallucinations — trigger p

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.agents/skills/ai-prompt-evaluator/SKILL.md · 62 lines

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.

Read it on GitHub

Changes

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.

  1. 11d ago First seen · 62 lines · 109 tokens per session scan B fe0fa957001a

Subscribe to this mod's changes

ai-prompt-evaluator is a skill published in the GitHub repository ieeecsopen/mcp-cs (3 stars, last pushed 7d ago), with no licence file. It adds 109 tokens to every session and 662 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (instruction-override phrasing, asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

compressed-system-prompts

Shorten repeated system-prompt wording while preserving task scope, requirements, and instruction priority.

alivirgo/Major-AI-Skills · 23 tokens

prompt-engineering-expert

Expert prompt engineering: prompt structure, few-shot, chain-of-thought, structured output, and iteration. Trigger keywords: prompt, prompt engineering, system prompt, few-shot, chain-of-thought, output format, JSON schema, structured output, instructions, role, examples, eval. Use for writing, debugging, or…

Miaoge-Ge/coding-agent-skills · 77 tokens

research-guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained gen...

GrayCodeAI/starling · 39 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

davila7/claude-code-templates · 38 tokens

coding-agents-prompt-authoring

To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.

griddynamics/rosetta · 39 tokens