wove: Skill for Claude Code

.claude/skills/online-order/SKILL.md

online-order is a skill for Claude Code from mits-pl/wove. It costs 104 tokens per session (2,085 once invoked), scanned C, original, Apache-2.0.

An assistant for finding and ordering products from Polish online marketplaces, including Allegro and Ceneo. It compares available options and helps with the purchase process.

In plain words
What is it for?
Researching products, comparing offers, adding a selected item to a cart, and handing off checkout.
Why use it?
It reduces the need to search several shops, compare prices manually, and track the checkout steps yourself.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is mits-pl/wove's own configuration. It tells Claude Code how to work on wove itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wove configures →

View source ↗ mits-pl/wove
Reuse

Borrowing it

Nothing to install: this file belongs to mits-pl/wove. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mits-pl/wove/main/.claude/skills/online-order/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mits-pl/wove

Made for: Claude Code.

Wrote 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.

agentmods badge for online-order

README.md
[![agentmods](https://agentmods.dev/badge/skills/mits-pl/wove/online-order/github.svg)](https://agentmods.dev/skills/mits-pl/wove/online-order)
Your own site
<a href="https://agentmods.dev/skills/mits-pl/wove/online-order"><img src="https://agentmods.dev/badge/skills/mits-pl/wove/online-order/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.

agentmods 80×15 button for online-order

Your own site · 80×15
<a href="https://agentmods.dev/skills/mits-pl/wove/online-order"><img src="https://agentmods.dev/badge/skills/mits-pl/wove/online-order.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,085 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.02085
Opus 5 $0.00052 $0.01043
Sonnet 5 $0.00021 $0.00417
Haiku 4.5 $0.00010 $0.00209

Measured 9d ago against content hash a527ec20d648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

online-order scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Delete research files: use `term_run_command` to run `rm -rf /tmp/order-research/`
.claude/skills/online-order/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Online Order: Product Research & Purchase Assistant

Search, compare, and order products across Polish online marketplaces.


Web Interaction Rules (MANDATORY — applies to ALL phases)

These rules override any other instinct. Follow them for EVERY web interaction:

  1. ALWAYS use web_capture before clicking or typing. Never guess CSS selectors. web_capture returns a screenshot with numbered element markers AND their exact CSS selectors. Use ONLY those selectors.
  2. Never guess selectors. If web_click fails, do NOT try another guessed selector. Instead call web_capture again to get the current page state and correct selectors.
  3. Verify state after every action. After adding to cart, use web_capture or web_read_text to confirm:
    • Did the cart count increase?
    • Did a confirmation popup appear?
    • Am I on the expected page?
  4. Never repeat a failed action. If a click/selector fails twice, STOP and rethink. Use web_capture to see the current state.
  5. One add-to-cart click only. After clicking "add to cart", verify the cart count. If it shows 1, you're done. Do NOT click again.
  6. Maximum 3 retries per step. If you fail 3 times at any step (e.g., finding a button, loading a page), inform the user and ask for guidance.
  7. CSS selectors only. Never use Playwright-style selectors like text=.... Only standard CSS selectors work with web_click and web_type_input.

Phase 1 — Clarify Requirements (MANDATORY — DO NOT SKIP)

STOP. Before doing ANYTHING else, you MUST complete this phase.

  1. If the product description ($ARGUMENTS) is vague, ask the user for specifics:
    • Brand, model, version
    • Size, color, capacity
    • Any other relevant attributes
  2. Ask the user about their priority:
    • Fast delivery — prioritize shortest delivery time
    • Lowest price — prioritize cheapest option
    • Compromise — best value (balance of price and delivery speed)
  3. Store the priority for decision-making in Phase 4.

Read the full file on GitHub · 181 lines

Changes

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.

  1. 9d ago First seen · 181 lines · 104 tokens per session scan C a527ec20d648

Subscribe to this mod's changes

online-order is a skill published in the GitHub repository mits-pl/wove (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,085 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

pricing-page

A standalone pricing page — header, plan tiers, feature comparison table, and an FAQ. Use when the brief asks for "pricing", "plans", "subscription tiers", or a "compare plans" page.

linyeping/Metis · 45 tokens

invoice

A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".

linyeping/Metis · 46 tokens

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

find-simplifications

Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…

QwenLM/qwen-code · 103 tokens

kunze-ad-setup

Codex-native Amazon PPC setup workflow using Kunze's broader ecosystem-driven strategy. Use when the user wants LaunchFast-driven bulk-sheet generation with broad and phrase coverage, gap analysis, and a campaign package written to disk.

hashgraph-online/awesome-codex-plugins · 53 tokens