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 agentmods add commands/emaraschio/cursor-commands/structure-promptgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/commands/emaraschio/cursor-commands/structure-prompt)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/structure-prompt"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/structure-prompt.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00655 |
| Opus 5 | $0.00017 | $0.00328 |
| Sonnet 5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
structure-prompt 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Compose a copyable, structured prompt from a rough ask by applying only the prompting dimensions that fit, then report what was applied or omitted. Produces a prompt; does not run the task. Full workflow: .cursor/skill-contracts/structure-prompt/SKILL.md (user install: ~/.cursor/skill-contracts/structure-prompt/SKILL.md).
Defaults
| Setting | Default |
|---|---|
| Dimensions | Apply only those that fit (product verification, structured high-stakes, constraints-upfront, scannable structure, search priority, internal-first) |
| Effort | Proportional to stakes; trivial asks get a light prompt, not the full template |
| Output | One copyable prompt block + an applied/omitted note |
| Model | Model-agnostic; no hardcoded model names or canonical leaked-prompt claims |
| Examples | Generic names only (service-a) |
Steps
- Read
.cursor/skill-contracts/structure-prompt/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/structure-prompt/SKILL.md. - Execute phases in order (Intake -> Classify -> Fill template -> Deliver).
- Report the structured prompt and the applied/omitted dimension note in chat.
Anti-patterns
- Match effort to stakes. Trigger: a simple or one-line request. Wrong: bolting on all six dimensions and dumping the full template. Correct: produce a light prompt proportional to the ask and note which dimensions are not applicable. Reason: over-engineering a trivial ask wastes the user's time and buries the actual request.
- Produce the prompt, do not run it. Trigger: finishing the structured prompt. Wrong: executing the underlying task the prompt describes. Correct: return the copyable prompt and stop. Reason: this skill builds prompts, and running the task skips the user's review of the prompt.
- Do not invent product facts. Trigger: the prompt asks about a tool's current capabilities. Wrong: asserting pricing, APIs, or a model name from memory. Correct: add a clause to verify against current docs and flag that product knowledge may be stale. Reason: stale or invented product claims propagate into every downstream answer.
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.
- 5d ago First seen · 46 lines · 35 tokens per session scan A 95af62837a5c
structure-prompt is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 29d ago), licensed MIT. It adds 35 tokens to every session and 655 once invoked, about $0.0002 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 commands, from other repositories
standalone-python-scripts
Command "standalone-python-scripts" from iloveitaly/llm-ide-rules, covering standalone python scripts, /// script, requires-python = ">=3.13", dependencies = [] and ///.
setup-models
Update the default LLM provider and model, optionally validate provider connectivity with a test API call.
setup-routing
Configure per-task LLM routing for Gnosys tasks.
stripe-backend
Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.
python-command
Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.
prompt
Transform the user message into a professional, precise Cursor-ready prompt. Never execute the requested task. Output only the optimized prompt package.