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 ceo-to-ceogit 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/ceo-to-ceo)<a href="https://agentmods.dev/skills/mishahanin/heading-os/ceo-to-ceo"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/ceo-to-ceo/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/ceo-to-ceo"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/ceo-to-ceo.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 | $0.00114 | $0.00873 |
| Opus 5 | $0.00057 | $0.00436 |
| Sonnet 5 | $0.00023 | $0.00175 |
| Haiku 4.5 | $0.00011 | $0.00087 |
Grade A, and why
ceo-to-ceo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEO-to-CEO Correspondence
Draft CEO-level correspondence to a partner, peer executive, or key institutional contact.
Variables
to: [CEO/executive name, title, company]
subject_area: [Core subject — e.g., "partnership expansion proposal", "post-MWC follow-up", "strategic alignment meeting"]
objective: [What this communication should achieve]
context: [Background on the relationship and situation]
tone: formal | warm-peer | urgent — default: warm-peer
Instructions
Before drafting, read:
reference/misha-voice.md— Voice guide, especially Email and CEO-to-CEO notescontext/people.md— Load full relationship context for this executivecontext/business-info.md— 31C positioning and partner contextcontext/pipeline.md— Check if this relates to an active partnership discussiondatastore/INDEX.md— If the post contains specific facts or numbers, validate against source documents
Draft a CEO-to-CEO communication that:
- Opens as a peer - not a vendor writing to a client, not a subordinate writing up
- Gets to the point in the opening paragraph
- Is direct about the objective without being transactional
- Demonstrates that Misha understands the other CEO's business and interests
- Proposes a concrete next step or decision point
- Closes with the captain's tone - decisive, warm, forward-looking
Voss layer: Apply per .claude/rules/voss.md. Skill-specific hooks: accusation audit on sensitive topics, normative leverage (reference their stated values/public commitments), next steps as calibrated questions. Full framework: reference/voss-negotiation.md.
Length: 150-300 words. CEOs don't read long emails.
After the draft, provide:
- Subject line options (2)
- One flag: anything that requires extra care given the relationship
NEVER
- NEVER send the letter. This skill drafts only — outbound send is always human-gated (lethal-trifecta control). The CEO sends or approves explicitly.
- NEVER invent shared history or commitments with the counterpart CEO — if the relationship context is thin, ask.
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 · 90 lines · 114 tokens per session scan A 1c4fc27382e6
ceo-to-ceo is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 114 tokens to every session and 873 once invoked, about $0.0006 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.