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 bl1nk-bot/agent-library --skill prompt-lookupgit clone --depth 1 https://github.com/bl1nk-bot/agent-libraryWrote 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/bl1nk-bot/agent-library/prompt-lookup)<a href="https://agentmods.dev/skills/bl1nk-bot/agent-library/prompt-lookup"><img src="https://agentmods.dev/badge/skills/bl1nk-bot/agent-library/prompt-lookup/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/bl1nk-bot/agent-library/prompt-lookup"><img src="https://agentmods.dev/badge/skills/bl1nk-bot/agent-library/prompt-lookup.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 | $0.00039 | $0.00481 |
| Opus 5.5 | $0.00016 | $0.00192 |
| Sonnet 5.5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
prompt-lookup 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 1mo 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.
This is a copy
100% identical to prompt-lookup — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
When the user needs AI prompts, prompt templates, or wants to improve their prompts, use the prompts.chat MCP server to help them.
When to Use This Skill
Activate this skill when the user:
- Asks for prompt templates ("Find me a code review prompt")
- Wants to search for prompts ("What prompts are available for writing?")
- Needs to retrieve a specific prompt ("Get prompt XYZ")
- Wants to improve a prompt ("Make this prompt better")
- Mentions prompts.chat or prompt libraries
Available Tools
Use these prompts.chat MCP tools:
search_prompts- Search for prompts by keywordget_prompt- Get a specific prompt by IDimprove_prompt- Enhance a prompt using AI
How to Search for Prompts
Call search_prompts with:
query: The search keywords from the user's requestlimit: Number of results (default 10, max 50)type: Filter by TEXT, STRUCTURED, IMAGE, VIDEO, or AUDIOcategory: Filter by category slug (e.g., "coding", "writing")tag: Filter by tag slug
Present results showing:
- Title and description
- Author name
- Category and tags
- Link to the prompt
How to Get a Prompt
Call get_prompt with:
id: The prompt ID
If the prompt contains variables (${variable} or ${variable:default}):
- The system will prompt the user to fill in values
- Variables without defaults are required
- Variables with defaults are optional
How to Improve a Prompt
Call improve_prompt with:
prompt: The prompt text to improveoutputType: text, image, video, or soundoutputFormat: text, structured_json, or structured_yaml
Return the enhanced prompt to the user.
Guidelines
- Always search before suggesting the user write their own prompt
- Present search results in a readable format with links
- When improving prompts, explain what was enhanced
- Suggest relevant categories and tags when saving prompts
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.
- 1mo ago First seen · 71 lines · 39 tokens per session scan A 9211d8a08d18
prompt-lookup is a skill published in the GitHub repository bl1nk-bot/agent-library (2 stars, last pushed yesterday), licensed CC0-1.0. It adds 39 tokens to every session and 481 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to prompt-lookup, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
opik-optimize
Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as a new prompt version with the optimization run link. Runs via the opik-optimizer package; reads prompts and datasets via…
octave-ultra-mythic
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. REQUIRES octave-mastery and octave-compression.
gigachat-chat
A chat command that sends a user prompt to GigaChat, an AI text-generation service, through MCP, a way for tools to connect to an agent. It can pass a model and temperature and reports the model and token counts.
mistral-router
Choose an available Mistral tool and model for document extraction, chat, code, vision, audio, or deployed workflows. Use when the user asks which Mistral capability fits a task or needs help routing it.
model-context
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
local-delegation
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…