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/ma2za/google-news-api/agents-mdgit clone --depth 1 https://github.com/ma2za/google-news-apiWrote 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/ma2za/google-news-api/agents-md)<a href="https://agentmods.dev/instructions/ma2za/google-news-api/agents-md"><img src="https://agentmods.dev/badge/instructions/ma2za/google-news-api/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 | $0.00763 | $0.00763 |
| Opus 5 | $0.00381 | $0.00381 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
google-news-api 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This is the canonical project context for every coding agent. Read it before assessing, planning, or changing the repository. Gemini-specific context may exist locally, but no agent may rely on Gemini discovery alone.
Mandatory context discovery
Read files by their known paths even when Git, ripgrep, or an ignore file hides them.
- Read
.agents/README.mdwhen it exists. - For any question about the next release, release readiness, roadmap, planned
work, or what to implement next, read all of
.agents/PRIVATE_RELEASE_PLAN.mdbefore answering or editing. - For release work, also read
.agents/FAILURE_RETROSPECTIVE.md,docs/releasing.md,CHANGELOG.md, andpyproject.toml. - Verify plan statuses against the latest Git tag and published PyPI version.
If the private plan is stale, update its local status before selecting the
first release that is not
Released. - Never infer that no plan exists from
rg --files,git status, or tracked files alone. Private maintainer context is intentionally excluded from Git.
The private plan, private metrics, future promises, secrets, and credentials
must never be committed or published. Generic operational instructions and
sanitized failure retrospectives belong in AGENTS.md or tracked .agents/
files so every agent receives them.
Project
This repository is a Python 3.9+ library, CLI, and optional MCP server for
fetching news from Google News through RSS with sync, async, URL decoding,
caching, and MCP support. Poetry owns dependencies, packaging, scripts, and the
lock file. The public package is google-news-api.
Read the relevant implementation, tests, and documentation before editing.
Keep changes focused and preserve existing public interfaces, defaults, JSON
keys, environment variables, console scripts, and MCP tool signatures as
required by docs/compatibility.md.
Development
- Use the existing style and the simplest working implementation.
- Add a regression test for every bug fix and offline tests for new behavior.
- Update user-facing documentation and
CHANGELOG.mdfor behavior changes. - Do not edit
poetry.lockunless dependency declarations change. - Never expose or commit
.envcontents, credentials, tokens, cookies, captured request headers, or local service-account files. - Preserve unrelated worktree changes.
- Tests must exercise actual logic. Integration fixtures must be frozen output from actual Google News RSS responses, not invented dummy responses.
- Include adversarial parser cases such as malformed XML, unusual encodings, and missing tags when relevant.
- On Windows, prefer
python -m <module>over direct executable shims to avoid application-control policy blocks.
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.
- 3d ago First seen · 81 lines · 763 tokens per session scan A 739b09d9021d
google-news-api AGENTS.md is an instructions file published in the GitHub repository ma2za/google-news-api (17 stars, last pushed 4d ago), licensed MIT. It adds 763 tokens to every session, about $0.0038 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
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
ai-research-arm CLAUDE.md
Instructions for guzus/ai-research-arm, covering claude.md, project overview, core pipeline architecture, key components and scripts (scripts/).
ai-research-arm AGENTS.md
Instructions for guzus/ai-research-arm, covering agents.md and agent-specific notes.
wdoc CLAUDE.md
Claude Code instructions for thiswillbeyourgithub/wdoc, covering claude.md, project overview, commands, install and test.
perigon-mcp-server AGENTS.md
Instructions for goperigon/perigon-mcp-server, covering agent guidelines for perigon mcp server, important, build/test commands, code style and perigon brand colors.
news-reviewer AGENTS.md
Instructions for mertcanciy/news-reviewer, covering agents.md, news reviewer, input, step 1 — source and step 2 — brief.