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 agentmods add skills/codeinfinity1/stram/email-operationsnpx skills add CodeInfinity1/Stram --skill email-operationsgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00038 | $0.00694 |
| Opus 5 | $0.00019 | $0.00347 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
email-operations 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Operations
Purpose
Support email work as a personal-assistant capability while respecting the current Stram native-tool boundary. Until a Stram-owned mail adapter exists, this skill drafts, summarizes, and plans email work from provided evidence instead of pretending to read or send mail directly.
When To Use
Use for email drafts, inbox summaries from pasted/exported email, follow-up wording, reply review, mail setup planning, or deciding what native mail tools need to be implemented.
Inputs And Evidence
- Pasted email, exported
.eml/text, thread summary, recipient list, subject, and desired tone. - Existing notes, meeting follow-ups, commitments, or relationship context.
- User approval for any external-visible draft or send.
- Native capability search/status output.
Tool Map
read_filewrite_noteemail_draft_preparegmail_draft_preparememory_writecognitive_commitment_recordcognitive_trigger_recordtool_searchcapability_surfacemessage-approval-policy
Workflow
- Determine whether the user needs summary, reply draft, new email, follow-up plan, or adapter implementation.
- Use only provided mail evidence unless a native mail adapter is added later.
- Extract sender, recipients, subject, dates, asks, commitments, deadlines, and risks.
- Draft concise emails with subject, greeting, body, ask, closing, and optional alternatives.
- Record commitments or reminders only when explicit and desired.
- For Gmail-style drafting, use
gmail_draft_preparewith explicit recipients, subject, body, and reason; verify the draft artifact path. - For real sending, report the missing native send adapter or route through a future Stram-owned email send tool with approval.
Native Implementation Boundaries
- Do not use external reference Himalaya, Gmail scripts, external reference plugins, or external mail packages as the skill implementation.
- Drafting is natively supported through Stram-owned draft artifact tools. Sending still requires a future Stram-owned Gmail/Outlook/IMAP/SMTP adapter with schemas, approvals, tests, and redaction.
- Do not scrape a mail UI with OS/browser tools unless the user explicitly asks and approves that path.
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.
- 2d ago First seen · 75 lines · 38 tokens per session scan A e532f1b0e3fe
email-operations is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 38 tokens to every session and 694 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.