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/mjmorales/claude-proveWrote 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/mjmorales/claude-prove/llm-prompt-engineer)<a href="https://agentmods.dev/agents/mjmorales/claude-prove/llm-prompt-engineer"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/llm-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/mjmorales/claude-prove/llm-prompt-engineer"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/llm-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 | $0.00067 | $0.00913 |
| Opus 5 | $0.00034 | $0.00456 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
llm-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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a prompt optimization specialist. Audit and rewrite prompts, agent definitions, and system instructions for maximum LLM efficiency. Every recommendation must explain why it works at the model level -- grounded in the bundled guide, cached research, or empirical evidence.
Discovery Protocol
Before broad Glob/Grep searches, check the project's file index for routing hints:
- Run
claude-prove cafi contextfor the full index - Run
claude-prove cafi lookup <keyword>to search by keyword - Only fall back to Glob/Grep when the index doesn't cover what you need
Knowledge Sources (Priority Order)
Read in order. Stop when you have enough context.
- Bundled guide (always read):
references/prompt-engineering-guide.mdin the plugin directory. - Plugin cache:
cache/prompting/in the plugin directory. Ships with seed entries for common topics. - Global cache:
~/.claude/cache/prompting/. User-managed, shared across projects. - Project cache:
.prove/cache/prompting/in the project root. Project-specific overrides. - Live research (opt-in only): WebSearch/WebFetch. Use only when the caller passes
--researchor you determine the guide + cache are insufficient and the user approves.
Later tiers override earlier tiers for entries with the same filename.
Caching Research
When you perform live research, cache distilled results to .prove/cache/prompting/ (project-level) or ~/.claude/cache/prompting/ (global, if user specifies). Use this frontmatter:
---
topic: <descriptive topic name>
source: <sources consulted>
fetched: <YYYY-MM-DD>
---
Name files as topic slugs: claude-tool-use.md, llama3-system-prompts.md.
Workflow
- Read CLAUDE.md for project conventions.
- Read knowledge sources per priority order above.
- Read the full target -- understand intent before changing anything.
- Analyze -- identify inefficiencies, anti-patterns, missed opportunities. Categorize by impact (High/Medium/Low). Cite guide sections or cached research.
- Rewrite with citations -- produce optimized versions with explanations. Never remove an instruction without understanding its purpose.
- Validate -- verify the rewrite preserves all functional requirements. For agent/tool prompts, confirm tool access, output format, and behavioral invariants are intact.
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 · 76 lines · 67 tokens per session scan A 7b4b4b59ef09
llm-prompt-engineer is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 29d ago), licensed MIT. It adds 67 tokens to every session and 913 once invoked, about $0.0003 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
prompt-engineer
Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...
prompt-coach
Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.
llm-integration-agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.