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/email-intelWrote 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-intel)<a href="https://agentmods.dev/skills/mishahanin/heading-os/email-intel"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/email-intel/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-intel"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/email-intel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 282 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 15 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 | $0.00111 | $0.04509 |
| Opus 5 | $0.00056 | $0.02254 |
| Sonnet 5 | $0.00022 | $0.00902 |
| Haiku 4.5 | $0.00011 | $0.00451 |
Grade A, and why
email-intel 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 5d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Intelligence -- Exchange Inbox Processor
Scans the configured 31C Exchange mailbox, groups conversations, categorizes actionable items, and proposes CRM logs, tasks, pipeline updates, knowledge notes, and new contacts. Nothing ships without Misha's approval.
State Files
- State:
outputs/operations/email-intelligence/state.json-- processed message IDs, conversation history, stats - Tasks:
outputs/operations/email-intelligence/tasks.md-- active and completed action items - Sweep actions:
outputs/operations/email-intelligence/sweep-actions-YYYY-MM-DD.json-- the numbered recommended-action list + per-action status (proposed/approved/skipped/executing/done/failed). Managed byscripts/email-sweep.py; this is the resumable trail behind the Phase 3 approval. CLI-readable (python scripts/email-sweep.py list). - Digests:
outputs/operations/email-intelligence/digest-YYYY-MM-DD.md-- daily run records
Action Router
| Invocation | Action |
|---|---|
/email-intel (no args) |
Process last 24 hours (Phases 0-5) |
/email-intel --hours 48 |
Process last 48 hours |
/email-intel --inbox-only |
Inbox only (skip sent) |
/email-intel --sent-only |
Sent only (skip inbox) |
Priority Classification
Every conversation gets a priority tag:
| Priority | Criteria | Examples |
|---|---|---|
| P1 | Revenue-impacting, deadline-driven, client/partner-facing, investor comms | Deal follow-ups, contract negotiations, investor DD, demo requests |
| P2 | Important but not time-critical, internal ops, recurring admin | Tribe coordination, vendor inquiries, conference logistics |
| P3 | Nice-to-have, informational, low urgency | Newsletters, general inquiries, FYI forwards |
Classification signals:
- Explicit urgency ("ASAP", "urgent", "today", "by EOD") -> P1
- Revenue/deal context (pipeline companies, pricing, proposals, contracts) -> P1
- Investor or board communication -> P1
- Tribe management, process, internal ops -> P2
- Research, documentation, informational -> P3
- When in doubt, classify one level higher
What ships with it
10 files 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.
- evals/benchmark.json 2.3 KB
- evals/cases/case-1-category-schema.json 581 B
- evals/cases/case-2-approval-gate.json 543 B
- evals/cases/case-3-no-spam-greeting.json 417 B
- evals/outcomes/case-1-crm-log-outcome.json 642 B
- evals/outcomes/case-2-crm-log-idempotent.json 632 B
- evals/outcomes/case-3-crm-log-no-contact.json 539 B
- references/digest-format.md 8.0 KB
- references/execution-templates.md 4.2 KB
- triggers.json 949 B
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.
- 5d ago Changed · +3 lines · -6 tokens per session 2e570a70839c
- 9d ago First seen · 294 lines · 117 tokens per session scan A f1cb73df650a
email-intel is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 111 tokens to every session and 4,509 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-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.
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.