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 baldaworks/promptkitty --skill promptkitty-assemblegit clone --depth 1 https://github.com/baldaworks/promptkittyWrote 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/baldaworks/promptkitty/promptkitty-assemble)<a href="https://agentmods.dev/skills/baldaworks/promptkitty/promptkitty-assemble"><img src="https://agentmods.dev/badge/skills/baldaworks/promptkitty/promptkitty-assemble/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/baldaworks/promptkitty/promptkitty-assemble"><img src="https://agentmods.dev/badge/skills/baldaworks/promptkitty/promptkitty-assemble.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 | $0.00078 | $0.00939 |
| Opus 5 | $0.00039 | $0.00469 |
| Sonnet 5 | $0.00016 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
promptkitty-assemble 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- assemble — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptKitty Assemble
Use promptkitty when installed. Otherwise use the pinned fallback npx --yes @baldaworks/[email protected] for every command in the task. Resolve this once and keep the same command form throughout the workflow.
Use only the public PromptKitty CLI. Do not read PromptKit component source files or fetch PromptKit from the network.
Discover and inspect
-
Reduce the task to a short intent query and search templates:
promptkitty search "<intent>" --type template --jsonRetry with fewer domain-specific words when needed. Use
promptkitty list --type template --jsononly when search cannot identify a candidate. -
Select the best template from its name, description, and category. If two candidates imply materially different workflows, explain the difference briefly and ask the user to choose.
-
Inspect the selected template:
promptkitty show "<template>" --jsonTreat every key in
metadata.paramsas required. Reuse values supplied by the user or available in task context. Ask for missing values; never invent them. An empty value is valid only when the user intentionally leaves that parameter empty.
Assemble the source
Use --param "<name>=<value>" for short values and --param-file "<name>=<path>" for files or long multiline input. Quote assignments so shell metacharacters remain data. Add composition flags only when the user requests or confirms them.
promptkitty assemble "<template>" \
--param "<name>=<value>" \
--param-file "<name>=<path>"
Interactive templates
When metadata.mode is interactive:
- Resolve every declared parameter and run a provisional assembly without writing it to the target project.
- Read the provisional prompt only far enough to identify its first questioning, validation, and user-confirmation gate.
- Perform that first phase with the user. Read-only inspection is allowed when already authorized and necessary to answer the phase. Do not edit files, generate deliverables, run side-effectful commands, commit, or continue past the first confirmation gate.
- Fold confirmed answers into the matching declared parameters. Append a concise preflight decision summary to
contextwhen that parameter exists; otherwise refine only semantically matching declared parameters. Never add undeclared parameters. - Re-run
assemblewith the enriched values. This is the final source prompt. Do not execute its later phases.
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.
- 10d ago First seen · 78 lines · 78 tokens per session scan A 34a5d7b7efe4
promptkitty-assemble is a skill published in the GitHub repository baldaworks/promptkitty (5 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 939 once invoked, about $0.0004 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 skills, from other repositories
prompt-improver
Transform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change…
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI…
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.