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/commands/nvzver/claude-marketplace/prompt-create)<a href="https://agentmods.dev/commands/nvzver/claude-marketplace/prompt-create"><img src="https://agentmods.dev/badge/commands/nvzver/claude-marketplace/prompt-create/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/commands/nvzver/claude-marketplace/prompt-create"><img src="https://agentmods.dev/badge/commands/nvzver/claude-marketplace/prompt-create.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 | $0.00010 | $0.00530 |
| Opus 5 | $0.00005 | $0.00265 |
| Sonnet 5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
prompt-create 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace. On load, print first:
=============== [prompt-engineer/commands/prompt-create.md] [prompt-engineer] ===============
Prompt Create
Goal: Create a new prompt file with all required sections filled.
Input: $ARGUMENTS (name of the new prompt)
Constraints:
- Do NOT leave placeholder text in the final file
- Do NOT skip any required section
Steps
- If component type not in input → ask: "(A) Agent, (B) Command"
- If name not in input → ask for name (kebab-case)
- Read knowledge files:
../knowledge/actor-ground-rules.md,../knowledge/separation-of-concerns.md→ actor format template and classification rules loaded - Ask user for:
- Goal (one sentence)
- Input description
- 1-3 constraints
- Determine file path:
- Agent →
.claude/agents/{name}.md - Command →
.claude/commands/{name}.md
- Agent →
- Generate file using actor format template from knowledge/actor-ground-rules.md:
- Agent: frontmatter (name, description with examples, tools) + body (Role, Goal, Input, Constraints, Steps, Output, Example Output)
- Command: frontmatter (name, description, allowed-tools) + body (Goal, Input, Constraints, Steps, Output, Example Output)
- Show the full generated content per the
../../core/skills/output/SKILL.mdRule 7 Delivery test (turn-final message, or carried in the approval gate'spreview) → take approval viaAskUserQuestion→ then write the file and confirm the path — show → approve → write per Rule 7 Authorization boundary; on reject, write nothing - Run prompt-review logic on new file → verify compliance
Output
Format — approve path: file path + compliance status, 2 lines. Reject path: one line stating nothing was written.
Example Output
Created: .claude/commands/lint-config.md
Review: 0 issues found.
(reject path: Rejected — nothing written.)
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 · 48 lines · 10 tokens per session scan A 826539d8b9bd
prompt-create is a command published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 15d ago), licensed MIT. It adds 10 tokens to every session and 530 once invoked, about $0.0001 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
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.
structured-output-doctor
Find LLM calls whose output is parsed as JSON and harden them with native structured output plus validate-and-retry.
token-cost-audit
Audit LLM call sites for token and cost waste, quantify the savings, and apply the safe wins.
p
Prompt optimizer · clarify only if needed, rewrite your request into a sharper prompt, then carry it out. Prefix --dry to stop at the rewrite.
fix-prompt
Fix and improve a rough prompt — show the cleaned version and the changes before acting on it.
prompt-history
Manage history of created and optimized prompts.