Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/intel-briefing-newsletterWrote 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/skills/mishahanin/heading-os/intel-briefing-newsletter)<a href="https://agentmods.dev/skills/mishahanin/heading-os/intel-briefing-newsletter"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/intel-briefing-newsletter/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/skills/mishahanin/heading-os/intel-briefing-newsletter"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/intel-briefing-newsletter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00087 | $0.03312 |
| Opus 5 | $0.00044 | $0.01656 |
| Sonnet 5 | $0.00017 | $0.00662 |
| Haiku 4.5 | $0.00009 | $0.00331 |
Grade A, and why
intel-briefing-newsletter 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 12d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intel Briefing Newsletter
Generate a branded 31C Intelligence Briefing newsletter with live world intelligence research. This is the PUBLIC-FACING newsletter - safe for Tribe distribution, LinkedIn, prospects, and external sharing. Contains zero confidential information. For CEO-only intelligence with business implications and action items, use /ceo-intel instead.
Variables
focus: [Optional - specific topic or region to emphasize, e.g., "GCC cybersecurity", "Africa telecom", "global markets"]
issue_number: [Optional - issue number, defaults to auto-detect from existing folders in outputs/intel/newsletters/]
Instructions
Classification: Semi-Public. Safe for Tribe distribution and external sharing. NEVER include confidential information.
Before drafting, read:
reference/newsletter-guide.md- Content structure, design system, confidentiality rules, image guidelinesreference/misha-voice.md- Voice and tone (especially Tribe Communications section)reference/dpi-market-intelligence.md- DPI market data for Market Depth sectioncontext/people.md- To know which names must NEVER appear in the newslettercontext/pipeline.md- To know which deals/clients must NEVER appear in the newsletter
Phase 1: Research (Parallel)
Before searching, read reference/search-domains.md for domain filtering configuration and the Stream-to-Topic Mapping table.
Run these searches in parallel to gather live intelligence. For each stream, use allowed_domains from the matching topic group(s) and always apply the Blocked Domains list as blocked_domains:
- Geopolitics & Security - WebSearch for major world events, conflicts, policy changes
allowed_domains: Geopolitics & Defense groupblocked_domains: Blocked Domains list
- Cybersecurity - WebSearch for cyber incidents, threat actors, vulnerabilities, breaches
allowed_domains: Cybersecurity + General Tech groupsblocked_domains: Blocked Domains list
- [Priority Region 1] - WebSearch for defense, cybersecurity, telecom developments
allowed_domains: [Priority Region 1] + Geopolitics & Defense groupsblocked_domains: Blocked Domains list
- [Priority Region 2] - WebSearch for the priority region and regional developments
allowed_domains: [Priority Region 2] + Geopolitics & Defense groupsblocked_domains: Blocked Domains list
- [Priority Region 3] - WebSearch for telecom, cybersecurity, infrastructure investment
allowed_domains: [Priority Region 3] + Telecom & DPI groupsblocked_domains: Blocked Domains list
- Markets & DPI - WebSearch for capital markets, DPI industry, telecom trends
allowed_domains: Markets & Finance + Telecom & DPI groupsblocked_domains: Blocked Domains list
- Perplexity Deep Research - Run with domain filtering:
python scripts/perplexity-research.py --domains "reuters.com,bbc.com,ft.com,bleepingcomputer.com,lightreading.com,darkreading.com,therecord.media" "current world events [focus area] cybersecurity telecom defense markets [current month] [current year]"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 278 lines · 87 tokens per session scan A d2b66586efe3
intel-briefing-newsletter is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,312 once invoked, about $0.0004 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 skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.