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 zjchenQAQ/petprompt --skill optimizegit clone --depth 1 https://github.com/zjchenQAQ/petpromptWrote 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/zjchenqaq/petprompt/optimize)<a href="https://agentmods.dev/skills/zjchenqaq/petprompt/optimize"><img src="https://agentmods.dev/badge/skills/zjchenqaq/petprompt/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/skills/zjchenqaq/petprompt/optimize"><img src="https://agentmods.dev/badge/skills/zjchenqaq/petprompt/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 | $0.00055 | $0.00369 |
| Opus 5.5 | $0.00022 | $0.00148 |
| Sonnet 5.5 | $0.00011 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
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 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.
What it actually says
PetPrompt — optimize a prompt (preview mode)
This is the manual, preview counterpart to PetPrompt's hook. The user wants to SEE a cleaner version of their prompt before running it.
When invoked:
- Take the user's rough request — their arguments if provided, otherwise their most recent message.
- Rewrite it so it follows prompt-engineering best practices: clear, direct, specific, unambiguous, well-structured.
Hard rules — this is a rephrasing, not an expansion:
- Preserve the meaning, intent, and scope EXACTLY.
- Do NOT add new requirements, features, steps, or acceptance criteria the user did not state or clearly imply. Do not pad — the result is usually similar length or shorter.
- Remove hedging, filler, and ambiguity; use precise, imperative phrasing.
- Use the current conversation and project memory (CLAUDE.md) ONLY to resolve ambiguous references (what "it" / "this" points to) and to use correct names/terminology — never to introduce new scope.
- If the prompt is already clear, say so and return it unchanged. Keep the user's language.
Output format:
- Print the rewritten prompt inside a fenced code block so it is easy to copy.
- Follow it with a single-sentence "What changed" note (about phrasing, not added scope).
- Do NOT execute the task. This is preview only — wait for the user to run it.
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 · 34 lines · 55 tokens per session scan A 9e06fa0e4993
optimize is a skill published in the GitHub repository zjchenQAQ/petprompt (2 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 369 once invoked, about $0.0002 per session on Opus 5.5. 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-design
A structured method for designing prompts, the instructions given to an AI system. It covers the situation, the desired output, constraints, context, user input, and replaceable variables.
prompt-evaluation
A structured method for testing and comparing prompts, the instructions given to an AI. It uses defined criteria, test examples, comparisons, scores, and a recommendation.
ai-automation
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
refine
Crossover layer between the user's intent and LLM execution: takes a raw prompt (terse, frustrated, ambiguous, or shorthand), resolves every vague reference to a concrete artifact, recalls past decisions and lessons, and compiles a verifiable execution contract BEFORE any code is touched. Invoke explicitly as $refine…
llm-eng-checks
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
kimi-k2-prompting
How to write effective prompts for Kimi K2.7 when delegating.