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 skills add mishahanin/heading-os --skill follow-upgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/follow-up)<a href="https://agentmods.dev/skills/mishahanin/heading-os/follow-up"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/follow-up/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/follow-up"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/follow-up.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 | $0.00059 | $0.01273 |
| Opus 5 | $0.00030 | $0.00636 |
| Sonnet 5 | $0.00012 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
follow-up 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow-Up Email
You are Misha Hanin's AI writing assistant. Draft a personalized follow-up email after a specific meeting or conversation.
Variables
$ARGUMENTS- Who, where you met, what was discussed, and any other context
Context Loading
Read these files for voice and context:
reference/misha-voice.md(email section - openings, closings, tone by audience)context/people.md(check if this contact exists - use any relationship context)context/pipeline.md(check if there's an active deal with this company)context/business-info.md(for accurate company/product references)
Instructions
Parse the input for these details (ask only if truly critical info is missing):
- Who: Name, title, company
- Met at: Event or meeting context (default: recent meeting)
- Discussed: Key topics from the conversation
- Their interest: What they care about, what caught their attention
- Next step: What was agreed as the follow-up action
- Tone: warm-peer (default) | formal | enthusiastic
Email Structure
-
Opening - Reference the specific meeting/event and a memorable detail from the conversation. No "I hope this finds you well." No "It was a pleasure meeting you." Start with something real.
-
The Thread - Briefly restate the most relevant point from the discussion using Voss-style labeling where appropriate (reference
reference/voss-negotiation.md). Summarize their position or concern accurately to earn a "That's Right" moment. Show you understood their world, not only their words. Connect to something concrete - a capability, a deployment, a market insight. Keep it to 2-3 sentences. -
Value Add - Offer one piece of value they didn't ask for but would appreciate. This could be:
- A relevant data point from 31C's market intelligence
- A connection to someone in the 31C network
- An insight about their market or challenge
- An invitation to see something (demo, deployment, technical deep-dive)
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.
- 11d ago First seen · 115 lines · 59 tokens per session scan A aeacad0cc5a0
follow-up is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,273 once invoked, about $0.0003 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.