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 skills add promptingbox/mcp --skill prompt-managementgit clone --depth 1 https://github.com/promptingbox/mcpWrote 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/skills/promptingbox/mcp/prompt-management)<a href="https://agentmods.dev/skills/promptingbox/mcp/prompt-management"><img src="https://agentmods.dev/badge/skills/promptingbox/mcp/prompt-management/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/skills/promptingbox/mcp/prompt-management"><img src="https://agentmods.dev/badge/skills/promptingbox/mcp/prompt-management.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 | $0.00000 | $0.00676 |
| Opus 5 | $0.00000 | $0.00338 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
prompt-management 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 8d 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.
Prompt Management Skill
You have access to PromptingBox — a prompt library where the user stores, organizes, and versions their AI prompts. Use the pbox MCP tools to interact with it.
When to proactively suggest saving a prompt
- The user has iterated on a prompt multiple times and reached a version they're happy with
- The user explicitly asks you to write a complex system prompt, persona, or instruction set
- The user says anything like "save this", "remember this prompt", "store this", or "bookmark this"
- The user creates a reusable prompt template (e.g., a code review checklist, writing style guide, analysis framework)
- The user refines a prompt and says something like "that's perfect" or "let's keep this version"
When suggesting a save, briefly explain what you'll save and ask for confirmation before calling save_prompt. Suggest a clear, descriptive title.
When to retrieve prompts
- The user says "get my prompt", "find my prompt about...", "what prompts do I have for..."
- The user wants to reuse or reference a previously saved prompt
- The user asks to list, browse, or organize their prompt collection
- Before writing a prompt from scratch, check if the user already has a similar one saved
Organization best practices
- Titles: Use clear, descriptive titles that make prompts easy to find later. Examples: "Code Review Checklist", "Blog Post Writer — Technical", "SQL Query Optimizer"
- Folders: Group related prompts together. Suggest folder names based on the prompt's domain (e.g., "Development", "Writing", "Analysis", "Marketing")
- Tags: Apply 1-3 relevant tags for cross-cutting concerns. Good tags describe the prompt's purpose or technique (e.g., "system-prompt", "chain-of-thought", "few-shot", "persona")
- Versioning: When updating an existing prompt, use
update_promptinstead of saving a new copy — this preserves version history automatically
Tool quick reference
| Action | Tool |
|---|---|
| Save a new prompt | save_prompt |
| Find a prompt | search_prompts or get_prompt |
| See all prompts | list_prompts |
| Update content (auto-versions) | update_prompt |
| Organize into folders | move_prompt_to_folder or create_folder |
| Tag prompts | add_tags |
| Browse public templates | search_templates then use_template |
| Check version history | list_versions |
| Revert to old version | restore_version |
| Check connected account | whoami |
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.
- 8d ago First seen · 50 lines · 0 tokens per session scan A 399de0b17f94
prompt-management is a skill published in the GitHub repository promptingbox/mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 676 tokens. 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 skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…