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 email-respondgit 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/email-respond)<a href="https://agentmods.dev/skills/mishahanin/heading-os/email-respond"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/email-respond/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/email-respond"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/email-respond.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 | $0.00092 | $0.00728 |
| Opus 5 | $0.00046 | $0.00364 |
| Sonnet 5 | $0.00018 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
email-respond 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.
What it actually says
Email Response
Draft a response to an incoming email in Misha's voice.
Variables
notes: [Any specific points to make, things to avoid, or context not visible in the email — optional]
[Paste the email to respond to below the divider]
[PASTE INCOMING EMAIL HERE]
Instructions
Before drafting, read:
reference/misha-voice.md— Voice guidecontext/people.md— Check if sender is listed; load relationship contextcontext/pipeline.md— Check if this relates to an active deal or conversation
Analyze the incoming email:
- What is the sender's real intent or question?
- What tone are they using?
- Is this a decision request, information request, relationship maintenance, or problem?
- Tactical empathy read: Apply Voss per
.claude/rules/voss.md. Surface emotions under the words; label tension/frustration before addressing substance; redirect demands with calibrated questions. Full framework:reference/voss-negotiation.md.
Draft a response that:
- Addresses the sender's actual intent (not just the surface question)
- Leads with the most important point
- Is appropriately brief — never longer than the incoming email unless complexity requires it
- Closes with a clear next step or acknowledgment
After the draft, provide:
- Subject line (if replying to a new thread or re-titling)
- One flag: anything to double-check before sending
NEVER
- NEVER send the reply. This skill drafts only — outbound send is always human-gated (lethal-trifecta control). The CEO sends or approves explicitly.
- NEVER fabricate facts or commitments not present in the incoming thread.
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 · 81 lines · 92 tokens per session scan A 96bc3faecf64
email-respond is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 728 once invoked, about $0.0005 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-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-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-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.