What is ai-news-agent AGENTS.md?

Repository instructions for an AI news agent that collects news and publishes a daily digest through GitHub Actions, GitHub's automated workflow service.

Use them when running, troubleshooting, or verifying the daily AI news digest.

They give the agent a fixed process for checking existing issues, handling feed failures, recording decisions, and confirming publication.

How nickzren/ai-news-agent configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nickzren/ai-news-agent. 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/nickzren/ai-news-agent/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nickzren/ai-news-agent

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nickzren/ai-news-agent/agents-md/github.svg)](https://agentmods.dev/instructions/nickzren/ai-news-agent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nickzren/ai-news-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/nickzren/ai-news-agent/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nickzren/ai-news-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/nickzren/ai-news-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,148 This file is loaded in full into every session.

When invoked 1,148 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01148	$0.01148
Opus 5.5	$0.00459	$0.00459
Sonnet 5.5	$0.00230	$0.00230
Haiku 4.5	$0.00115	$0.00115

Measured 1mo ago against content hash 42a37d41fb08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-news-agent 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 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI News Agent

Purpose

Build the daily AI digest locally with an agent.
Publish the final issue through GitHub Actions so the issue author is app/github-actions.

Where To Look

README.md is for newsletter readers only; keep it free of developer detail.
docs/development.md: setup, CI and scheduled runs, API response contract, agent-driven mode and decision schema, feed configuration.
docs/architecture.md: pipeline diagrams and design notes.
docs/follow-ups.md: known limitations.
feeds.json: news sources.

Verify Changes

UV_CACHE_DIR=.uv-cache uv sync --locked --extra dev
UV_CACHE_DIR=.uv-cache uv run pytest -q
UV_CACHE_DIR=.uv-cache uv run mypy src

Preferred Agent Flow

UV_CACHE_DIR=.uv-cache uv sync --locked
uv run python src/main.py --check-issue --issue-status-file digest-issue-status.json
Stop if digest-issue-status.json says ok: true and exists: true.
Stop if it says ok: false and retryable: false.
If it says ok: false and retryable: true, continue.
RSS_MAX_WORKERS=2 RSS_TIMEOUT=15 uv run python src/main.py --candidates-only --status-file digest-run-status.json
If digest-run-status.json says feed_fetch_failed or empty_snapshot_with_feed_errors, retry once with RSS_MAX_WORKERS=1 RSS_TIMEOUT=20.
If the retry still fails, stop and report the failure reason.
If status is healthy, write digest-decisions.json using the repo decision schema.
uv run python src/main.py --apply-decisions digest-decisions.json
uv run python src/main.py --dispatch-publish
Wait briefly, then re-run --check-issue to confirm the issue exists.

Defaults

Prefer the agent path above for daily runs.
Do not use uv run python src/main.py for the daily automation path unless explicitly asked. That is the repo's default graph path and may use the repo LLM API path.
--publish-issue is a manual fallback only.
--dispatch-publish is the normal final publish path.
--dispatch-publish needs workflow-dispatch-capable GitHub auth through authenticated local gh, or through DIGEST_GITHUB_TOKEN, GITHUB_TOKEN / GH_TOKEN in CI-style environments.
For local Codex automation, use authenticated local gh; if it fails with 401, re-authenticate gh instead of switching the runbook to direct publish.

Read the full file on GitHub · 72 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.

1mo ago Changed · +16 lines · +219 tokens per session 42a37d41fb08
1mo ago Changed · +1 lines · +105 tokens per session b8d3e76d1579
2mo ago Changed · +5 lines · +126 tokens per session eafce82eda9d
2mo ago First seen · 50 lines · 698 tokens per session scan A 4b7b0fd02d2c

Subscribe to this mod's changes

ai-news-agent AGENTS.md is an instructions file published in the GitHub repository nickzren/ai-news-agent (2 stars, last pushed 3d ago), licensed MIT. It adds 1,148 tokens to every session, about $0.0046 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.

CI and CD DevOps and cloud LLM Research agentic-ai ai automation daily-digest github-actions

ai-news-agent AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-news-agent AGENTS.mdnickzren/ai-news-agent	Instructions file	2	3d ago	MIT	A	1,148	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-news-agent: Instructions file for Codex