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 agentmods add instructions/flack0x/trendspyg/agents-mdgit clone --depth 1 https://github.com/flack0x/trendspygWrote 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/instructions/flack0x/trendspyg/agents-md)<a href="https://agentmods.dev/instructions/flack0x/trendspyg/agents-md"><img src="https://agentmods.dev/badge/instructions/flack0x/trendspyg/agents-md.svg" alt="Measured on agentmods" 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 | $0.04378 | $0.04378 |
| Opus 5 | $0.02189 | $0.02189 |
| Sonnet 5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
trendspyg AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Reference for coding agents (Claude Code, Codex, Gemini CLI, Cursor, etc.) working with the trendspyg library. Human-written; agent-readable. Keep it short — link out for depth.
What this library does
trendspyg is a Python library + CLI for Google Trends data. It is the maintained replacement for the archived pytrends. Three paths:
- RSS path (
download_google_trends_rss) — fast (typically 0.2–2s, network-dependent), ~10–20 current trends per region, includes news articles and images, no browser required. Use this by default for "what's trending now?" - CSV path (
download_google_trends_csv) — comprehensive (~10s), 480+ current trends, supports time/category filtering, requires Chrome + Selenium. Use when you need the extra volume or filtering. - Explore path (
download_google_trends_interest_over_time,download_google_trends_explore,download_google_trends_comparison) — keyword analysis over time (interest over time, related queries, interest by region, multi-keyword comparison on one shared scale) — the datapytrendswas most used for. Requires Chrome; rate-limit sensitive (~10–90s, may retry) — roughly 8–10 fresh browser sessions in a short burst triggers Google's hard 429 block for the machine's IP (RateLimitErrorat once; recovery tens of minutes at least). Use for "how is interest in keyword X moving / where does it peak / which of these terms wins?", not for high-frequency polling; identical repeats are free withcache="disk".
Install
pip install trendspyg[all] # everything
pip install trendspyg # core (RSS path + CSV path, no CLI/async/DataFrame)
pip install trendspyg[cli] # CLI only
pip install trendspyg[async] # async RSS
pip install trendspyg[analysis] # DataFrame/JSON/Parquet output
pip install trendspyg[mcp] # MCP server (Python 3.10+)
MCP server — the zero-code path
If your host supports MCP, you don't need to write Python at all: register the
trendspyg-mcp command (stdio) and call the tools directly.
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.
- 4d ago First seen · 301 lines · 4,378 tokens per session scan A 02e85540d042
trendspyg AGENTS.md is an instructions file published in the GitHub repository flack0x/trendspyg (46 stars, last pushed 15d ago), licensed MIT. It adds 4,378 tokens to every session, about $0.0219 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.
Other instructions, from other repositories
stata-code AGENTS.md
Instructions for brycewang-stanford/stata-code, covering agents.md — stata-code project notes, communication, release coordination, pypi / testpypi trusted publishing — what to know and recovery: invalid-publisher failure.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
pygwalker CLAUDE.md
Instructions for Kanaries/pygwalker, covering claude.md and tl;dr for a coding agent.
apm python.instructions.md
Python development guidelines.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).