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-optimize)<a href="https://agentmods.dev/commands/nvzver/claude-marketplace/prompt-optimize"><img src="https://agentmods.dev/badge/commands/nvzver/claude-marketplace/prompt-optimize/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-optimize"><img src="https://agentmods.dev/badge/commands/nvzver/claude-marketplace/prompt-optimize.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 | $0.00012 | $0.00675 |
| Opus 5 | $0.00006 | $0.00338 |
| Sonnet 5 | $0.00002 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
prompt-optimize 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 — 50 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-optimize.md] [prompt-engineer] ===============
Prompt Optimize
Goal: Fix ground rule violations in target prompts.
Input: $ARGUMENTS (file path, directory, or glob pattern). If empty or ambiguous, ask: "(A) specific file, (B) all prompts in a plugin directory, (C) all prompts in the repository"
Constraints:
- Do NOT change the functional intent of any prompt
- Do NOT add features or content beyond what ground rules require
- Do NOT proceed without reviewing first
Steps
- Read knowledge files:
../knowledge/actor-ground-rules.md,../knowledge/quality-checks.md,../knowledge/separation-of-concerns.md→ checklist loaded - Run prompt-review logic on target → issues table
- If no issues found → report "No issues found." and stop
- Present issues table to user → confirm scope of fixes
- For each file with issues, apply fixes by severity:
a. HIGH: add missing sections using actor format template from knowledge/actor-ground-rules.md → file contains all required sections
b. MEDIUM: apply fixes per knowledge/quality-checks.md and knowledge/actor-ground-rules.md — rewrite vague steps with arrow-notation results, consolidate duplicates, replace hardcoded formats with knowledge references, merge constraints, remove restated descriptions
c. LOW: delete adverbs, replace hedging with direct statements, convert passive to active voice, remove filler phrases, add paradigm citations, trim example bloat, remove low-density padding
5.5. Quote each applied fix inline before the verdict (write, show, comment) per
../../core/skills/output/SKILL.mdRule 7 — the Step 8 change table is the compressed-inspection-table form; for a small batch, show before/after per edit. Never report "fixed N issues" without the changed content. - Re-run review on modified files → verify fixes resolved issues
- If new issues found → repeat steps 5-6 until no new issues remain or the same issue recurs
- Compile changes → output table
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 · 50 lines · 12 tokens per session scan A 93c001019efa
prompt-optimize is a command published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 14d ago), licensed MIT. It adds 12 tokens to every session and 675 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.