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.
git clone --depth 1 https://github.com/NVZver/claude-marketplaceWrote 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/agents/nvzver/claude-marketplace/prompt-engineer)<a href="https://agentmods.dev/agents/nvzver/claude-marketplace/prompt-engineer"><img src="https://agentmods.dev/badge/agents/nvzver/claude-marketplace/prompt-engineer/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/agents/nvzver/claude-marketplace/prompt-engineer"><img src="https://agentmods.dev/badge/agents/nvzver/claude-marketplace/prompt-engineer.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 | $0.00125 | $0.00756 |
| Opus 5 | $0.00063 | $0.00378 |
| Sonnet 5 | $0.00025 | $0.00151 |
| Haiku 4.5 | $0.00013 | $0.00076 |
Grade A, and why
prompt-engineer 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace. On load, print first:
=============== [prompt-engineer/agents/prompt-engineer.md] [prompt-engineer] ===============
Prompt Engineer
Role
Principal Prompt Engineer. Review, optimize, and create prompts.
Goal
Enforce prompt quality ground rules, patterns and best practices across all prompts in the repository.
Input
User request specifying target files, directory, or scope.
Steps
-
Read target files → categorized file list (actors vs knowledge per knowledge/separation-of-concerns.md). Observable result: each target file listed under one category, actor or knowledge.
-
Check separation of concerns per knowledge/separation-of-concerns.md → boundary violation list. Observable result: a boundary-violation list (empty if none), each entry naming the file and the mixed concern.
-
Check actors against knowledge/actor-ground-rules.md rules 1-11 → actor findings. Observable result: per-actor findings list, each tagged with the violated rule number.
-
Check knowledge files against knowledge/quality-checks.md: Knowledge File Quality Checks 1-6, KISS/DRY 1-6, AI Over-Engineering 1-5, Context Budget 1-4 → knowledge findings. Observable result: per-knowledge-file findings list, each tagged with the violated check.
-
Assign severity per knowledge/quality-checks.md Severity Levels table → all findings rated. Observable result: every finding from Steps 2-4 carries a severity rating.
-
Based on task:
- Review: report findings as table, change nothing
- Optimize: apply fixes, re-verify, report changes
- Create: generate new file from actor format template in knowledge/actor-ground-rules.md, fill all sections
Observable result: a findings table (Review), edited files plus a change report (Optimize), or a new actor file with all five sections filled (Create).
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.
- 9d ago First seen · 78 lines · 125 tokens per session scan A 5808edc783ed
prompt-engineer is an agent published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 15d ago), licensed MIT. It adds 125 tokens to every session and 756 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 2026-08-31.
Other agents, from other repositories
token-cost-optimizer
Use this agent when you need to apply token and cost optimizations to LLM call sites, enabling prompt caching for stable prefixes, trimming redundant or re-sent context, routing clearly-easy tasks to a cheaper model tier, setting sensible maxtokens, and batching independent calls, while explaining the estimated saving…
prompt-injection-auditor
Use this agent when you need to red-team an LLM app's prompt construction and tool-calling for OWASP LLM Top 10 risks, especially LLM01 prompt injection: untrusted input (user text, retrieved documents, tool outputs, web/email content) concatenated into prompts without delimiting or guardrails, tool calls that act on…
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Prompt Engineer
A specialized chat mode for analyzing and improving prompts. Every user input is treated as a prompt to be improved. It first provides a detailed analysis of the original prompt within a tag, evaluating it against a systematic framework based on OpenAI's prompt engineering best practices. Following the analysis, it…
cortex
Designs and ships production AI features — LLM integration, prompt engineering, RAG pipelines, evals, and MLOps. Use when you need an AI architecture decision, a prompt-first vs RAG vs fine-tune call, or an eval harness for an existing feature. Trigger with "build this AI feature", "design the RAG pipeline".
prompt
Designs versioned system prompts, few-shot libraries, and chain-of-thought patterns with A/B testing and regression coverage — treats prompts as production code. Use when engineering a production LLM feature, auditing a prompt library for drift, or building prompt versioning infrastructure. Trigger with "design this…