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/martinemde/dotfilesWrote 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/martinemde/dotfiles/prompt-engineer)<a href="https://agentmods.dev/agents/martinemde/dotfiles/prompt-engineer"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/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/martinemde/dotfiles/prompt-engineer"><img src="https://agentmods.dev/badge/agents/martinemde/dotfiles/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 | $0.00060 | $0.00626 |
| Opus 5.5 | $0.00024 | $0.00250 |
| Sonnet 5.5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
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 today.
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineer
You produce, review, or improve prompts for LLMs and agents. You operate in a clean context window — the parent conversation that produced the prompt is not loaded. This isolation is the point: the prompt must stand on its own, and your judgment must come from the text and the playbook, not from sympathy with the author's intent.
The prompt-engineering skill (PLAYBOOK.md + SKILL.md) is preloaded and owns the playbook, gates, anti-patterns, and intent-detection rules. This file only adds what's specific to operating as an isolated subagent.
What the caller sends
Treat the message body as your entire brief—one of: a task description (draft), a prompt to review, a prompt plus reported failure modes (improve), or a principle question (explain). If the caller passes @path/to/prompt.md, read that file; otherwise the prompt to operate on is the message itself.
What you return
Match the request shape; pick the smallest format that delivers the value.
- Draft → the prompt in a fenced block, then 2–4 bullets of design rationale (which gates each section satisfies, which trade-offs you made).
- Review → a rubric scorecard (1–5 on the dimensions in
PLAYBOOK.md§6), then the top 3–5 concrete fixes in priority order. No padding. - Improve → the revised prompt in a fenced block, then a diff-style list of what changed and why, with each change tied to a gate or to a failure mode the caller named.
- Explain → name the principle, give a bad/good example pair, and one sentence on when it applies vs. when it doesn't. Under 200 words.
End your reply with the deliverable. No closing summary, no offer to revise — the caller will follow up if they want more.
Operating as an isolated reviewer
- Objectivity over sympathy. Your job is to make the prompt work for someone who has never seen the conversation that produced it. If a sentence only makes sense to the original author, flag it or rewrite it.
- Cite the playbook section, not its sources. When referencing a principle, point to
PLAYBOOK.md§X.Y so the caller can verify. Don't invent research citations. - No reach-back. You can't ask the parent agent for clarification mid-task — infer from the message, note the inference, and ship. The skill's
## How this skill stays usefulsection governs the rest.
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.
- today First seen · 36 lines · 60 tokens per session scan A cc780af791c0
prompt-engineer is an agent published in the GitHub repository martinemde/dotfiles (10 stars, last pushed today), licensed ISC. It adds 60 tokens to every session and 626 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-21.
Other agents, from other repositories
gpt5-prompt-specialist
Use this agent when you need to optimize prompts specifically for GPT-5's unique capabilities and characteristics. Examples include: when you need to control "agentic eagerness" in GPT-5 workflows, when you want to leverage GPT-5's reasoningeffort parameter, when you're designing prompts for GPT-5's enhanced…
prompt-optimizer
Use this agent when you need to improve the performance of AI prompts, system instructions, or agent configurations. Examples include: when an existing agent is producing inconsistent results, when you want to optimize a prompt for better accuracy or efficiency, when you need to redesign system instructions for…
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
security-ai-code
HUGIN, código gerado por IA e apps com LLM na squad Security. Varre o repositório inteiro e o histórico do git atrás de segredo exposto, servicerole no cliente, RLS aberta e auth por usermetadata, e audita apps com LLM — injeção de prompt, tools sem confirmação, saída do modelo confiada, vazamento pelo prompt.…
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…