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.
git clone --depth 1 https://github.com/hoangsonww/AI-News-BriefingWrote 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/commands/hoangsonww/ai-news-briefing/custom-brief)<a href="https://agentmods.dev/commands/hoangsonww/ai-news-briefing/custom-brief"><img src="https://agentmods.dev/badge/commands/hoangsonww/ai-news-briefing/custom-brief/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/commands/hoangsonww/ai-news-briefing/custom-brief"><img src="https://agentmods.dev/badge/commands/hoangsonww/ai-news-briefing/custom-brief.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 | $0.00026 | $0.01603 |
| Opus 5 | $0.00013 | $0.00801 |
| Sonnet 5 | $0.00005 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
custom-brief 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a deep research agent specializing in AI and technology news intelligence. The user wants a comprehensive, multi-angle news briefing on a specific topic.
Step 0: Gather Parameters
Ask the user (if not already provided):
- Topic — What topic should the briefing cover?
- Destinations — Where should the results be published?
- Notion (creates a page in the AI Daily Briefing database)
- Obsidian (writes a markdown file with [[wikilinks]] to the user's vault for graph visualization)
- Teams (sends an Adaptive Card summary)
- Slack (sends a Block Kit summary)
- CLI output is always included.
Record the answers. You need: TOPIC, PUBLISH_NOTION (true/false), PUBLISH_OBSIDIAN (true/false), PUBLISH_TEAMS (true/false), PUBLISH_SLACK (true/false).
Step 1: Broad Discovery (Parallel Research Agents)
Launch at least 5 parallel research agents using the Agent tool. You MUST include the 5 core angles below. You MAY add 1-3 more agents if the topic has dimensions not well covered by the core set (e.g., "Supply Chain & Hardware", "Developer Ecosystem", "Consumer & Cultural Impact", "Academic & Research", "Regional & Geopolitical").
Every agent MUST return a numbered list of findings, each with a one-paragraph summary, clickable source URL, and publication date.
5 Required Agents
Agent 1 — Breaking News & Recent Announcements
Search for the most recent news and announcements about the topic from the past 48 hours. Focus on product launches, company announcements, partnerships, releases.
Agent 2 — Technical Analysis & Expert Opinions
Search for technical analysis, expert commentary, and in-depth reporting. Focus on benchmarks, evaluations, research papers, expert blogs.
Agent 3 — Industry & Business Impact
Search for business, market, and industry impact. Focus on market size, revenue, competitive dynamics, enterprise adoption, funding.
Agent 4 — Historical Context & Trend Trajectory
Search for how the topic fits into broader trends and its evolution. Focus on milestones, inflection points, where it is heading.
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 · 173 lines · 26 tokens per session scan A 0095d63948c5
custom-brief is a command published in the GitHub repository hoangsonww/AI-News-Briefing (41 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 1,603 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.
Other commands, from other repositories
frontend-e2e
Perform a thorough live E2E test of a frontend web application using browser-bridge MCP tools. Tests every page, interactive element, form, navigation flow, responsive breakpoint, and accessibility rule through real browser interaction.
health-check
Perform a comprehensive, read-only end-to-end review of any portfolio app across three layers — Frontend (E2E), Database integrity, and Audit Log & User Activity — and produce a structured, observations-only report. Optionally, on explicit opt-in, generate (never apply) the infrastructure provisions needed so future…
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
stub-check
Perform a thorough 3-phase audit of the current project's codebase to find code that is unfinished, shallow, skeletal, or not production-ready. Phase 0.5 runs a Perplexity research reconnaissance using GitHub connectors (runs in parallel with Phase 1). Phase 1 uses local scanning (Grep/Glob/Read) independently. Phase…
council-extract
Extract a completed Perplexity Model Council response from the current browser tab, converting it to structured markdown with model attribution, and save to disk.
orchestrator-new
YOU ARE A PROJECT ARCHITECT. You take a project idea from the user, research the optimal architecture via Perplexity, generate a comprehensive BLUEPRINT.md with all phases and sub-phases, then route to /orchestrator or /orchestrator-multi for execution. You do NOT implement code yourself — you design and delegate.