Borrowing it
Nothing to install: this file belongs to mertcanciy/news-reviewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mertcanciy/news-reviewer/main/AGENTS.mdgit clone --depth 1 https://github.com/mertcanciy/news-reviewerWrote 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/mertcanciy/news-reviewer/agents-md)<a href="https://agentmods.dev/instructions/mertcanciy/news-reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/mertcanciy/news-reviewer/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.
<a href="https://agentmods.dev/instructions/mertcanciy/news-reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/mertcanciy/news-reviewer/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01409 | $0.01409 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
news-reviewer 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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository ships one capability: turning a news item into a research briefing rather than a summary. Any agent reading this file can perform it.
Invoke it when the user hands you a news link, a pasted article, or a headline and wants to understand or discuss it — not when they want code written.
The full instruction set follows. It is generated from
skills/news-reviewer/SKILL.md; edit that file and run scripts/sync.sh
rather than editing below this line.
News Reviewer
Turn a news item into a briefing — the prep document a researcher hands someone about to discuss the story: verified facts, context that deepens the discussion, and questions that open debate. A briefing is not an op-ed: every sentence in it is a verifiable fact, sourced context, or a question. Predictions and recommendations stay out.
Write the briefing in the language the user is conversing in, whatever language the sources are in. Translate quotes; keep the original alongside when precision matters.
Input
The user gives a news item: pasted text, a headline, or a link — optionally with a depth marker ("main story" / "quick note", expressed in whatever language the user speaks). Several items in one invocation: brief each in turn.
Step 1 — Source
- Link given: read it, then cross-check against at least one independent source.
- No link: search until you hold at least two independent sources (mix international and local where relevant).
Done when every load-bearing claim traces to a source. Mark claims only one source supports ("single source"), and state contradictions between sources explicitly — the user will repeat these claims to others.
Step 2 — Brief
| Section | Contents |
|---|---|
| Summary | A one-or-two-sentence lede in plain language — what is really going on here, told the way you'd tell a colleague — then 2–4 bullets carrying the specifics |
| Depth & Context | The material the user researches with: historical parallels, related developments, second-order effects. Each parallel carries one sentence on why it fits and where it breaks down. |
| Devil's Advocate | Questions that challenge the consensus narrative — pointed enough to open a real debate. Leave them unanswered; the discussion is the user's job. |
| Sources | Linked list |
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.
- 11d ago First seen · 73 lines · 1,409 tokens per session scan A 0a17ee5f5d95
news-reviewer AGENTS.md is an instructions file published in the GitHub repository mertcanciy/news-reviewer (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0070 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 2026-08-31.
Other instructions, from other repositories
agent-rulescope copilot-instructions.md
Copilot instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.
agent-rulescope tests.instructions.md
Instructions for 13624725933/agent-rulescope, a project described as: See exactly which instructions your coding agent inherits. Scan AGENTS.md, CLAUDE.md, Cursor and Copilot rules.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.