price-watch

price-watch is a skill for Claude Code, Codex from spyrae/kronos-agent-os. It costs 17 tokens per session (602 once invoked), scanned A, original, MIT.

A scheduled check of a product page that reports when the listed price crosses a chosen threshold. It is designed to run for a defined period and watch the actual product listing.

In plain words
What is it for?
It is for waiting for a product to fall below a target price, or cross another specified price condition, and notifying you when that happens.
Why use it?
It avoids repeatedly checking a page yourself and reduces distracting alerts caused by small price fluctuations. Checking the exact product page also prevents tracking the wrong item.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for waiting for a product to fall below a target price, or cross another specified price condition, and notifying you when that happens.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spyrae/kronos-agent-os/price-watch
Install

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.

Any agent
npx skills add spyrae/kronos-agent-os --skill price-watch
Clone the repo
git clone --depth 1 https://github.com/spyrae/kronos-agent-os

Made for: Claude Code, Codex.

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 price-watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/price-watch/github.svg)](https://agentmods.dev/skills/spyrae/kronos-agent-os/price-watch)
Your own site
<a href="https://agentmods.dev/skills/spyrae/kronos-agent-os/price-watch"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/price-watch/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 price-watch

Your own site · 80×15
<a href="https://agentmods.dev/skills/spyrae/kronos-agent-os/price-watch"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/price-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.00602
Opus 5 $0.00009 $0.00301
Sonnet 5 $0.00003 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 10d ago against content hash 2fb04e61f669, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

price-watch 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.

templates/skill-packs/marketplace/skills/price-watch/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Price Watch

Set it up as a plan, not a reminder

A watch is a plan step parked on a condition. plan_start with the goal in the owner's words, then plan_add_step with:

{"kind": "page_number", "url": "<product page>",
 "pattern": "Rp ([0-9.]+)", "op": "below", "value": 9000000,
 "every_seconds": 3600}

and notify: true on that step — a price crossing the line is exactly what the owner asked to be interrupted for.

Three details decide whether this works:

  • Watch the product page, never a search or category page. Search results reorder, and the number you captured yesterday belonged to a different item.
  • Check the pattern once by hand with fetch_page before parking the step. A pattern that matches nothing waits forever and reports nothing, which is indistinguishable from a price that never moved.
  • Give the plan an expiry. Most watches stop being wanted long before they stop running.

What counts as worth saying

A threshold, not a change. Marketplace prices jitter by a percent or two daily, and a message for each jitter is a message the owner turns off — after which the real drop arrives in a muted channel.

  • If the owner named a target price, that is the threshold.
  • If they said "let me know if it gets cheaper", propose one — around 10% below today's price is a starting point, and confirm it rather than guessing silently.
  • Fire on crossing, not on being below. The condition fires once, the step runs once, and that is the end of it unless the owner asks for another watch.

When it fires

The condition hands you what it saw — the price, and where. Do not re-fetch to find out why you woke; the page may have changed in between and you would report something the owner was not alerted about.

Say: the price now, the price when the watch started, the threshold, and the link. Then stop. A watch that fires and then keeps watching without being asked is a subscription nobody agreed to.

When it does not fire

Read the full file on GitHub · 68 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. 10d ago First seen · 68 lines · 17 tokens per session scan A 2fb04e61f669

Subscribe to this mod's changes

price-watch is a skill published in the GitHub repository spyrae/kronos-agent-os (49 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 602 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

python-lib-analyzer

Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.

shibing624/agentica · 23 tokens

data-visualization

Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.

langchain-ai/deepagents · 40 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

deepagents-thread-inspector

Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…

langchain-ai/deepagents · 82 tokens