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/jtsternberg/claude-plugins/gmail-draft-from-markdownnpx skills add jtsternberg/claude-plugins --skill gmail-draft-from-markdowngit clone --depth 1 https://github.com/jtsternberg/claude-pluginsWrote 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/jtsternberg/claude-plugins/gmail-draft-from-markdown)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/gmail-draft-from-markdown"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/gmail-draft-from-markdown.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.04146 |
| Opus 5 | $0.00024 | $0.02073 |
| Sonnet 5 | $0.00010 | $0.00829 |
| Haiku 4.5 | $0.00005 | $0.00415 |
Grade A, and why
gmail-draft-from-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Draft from Markdown
Take a local markdown file, convert it to HTML, and save it as a Gmail draft (never sent). Returns a clickable Gmail drafts URL so the user can review and send from the Gmail UI.
Default is --draft, always. Thoughtful emails (coaching follow-ups, client
notes, anything personal) need human review before they go out. This skill
will never send an email directly.
Prerequisites
# Codex: this path resolves under Claude Code; substitute the directory containing this plugin.
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
bash "$PLUGIN_ROOT/scripts/auth-preflight.sh"
Also requires a markdown→HTML converter. The script prefers
marked (npm i -g marked) and
falls back to pandoc. It errors with a clear message if neither is
installed.
Task
Run the entrypoint script, passing all arguments through:
# Codex: this path resolves under Claude Code; substitute the directory containing this SKILL.md.
SKILL_DIR="${CLAUDE_SKILL_DIR}"
bash "$SKILL_DIR/scripts/draft.sh" $ARGUMENTS
If no arguments were provided, ask the user for the markdown file path and
recipient (email or name). Subject is optional — the script derives it from a
Subject: ... line at the top of the markdown if present.
Arguments
| Arg | Required | Notes |
|---|---|---|
<markdown-file> |
yes | Path to a local .md file. |
<recipient> |
yes | Email address, or a name to look up via Gmail search. |
--subject "..." |
no | Overrides the Subject: line in the markdown. |
--cc EMAIL |
no | Comma-separated. |
--bcc EMAIL |
no | Comma-separated. |
--from EMAIL |
no | Send-as alias (defaults to active account). |
--reply-to MESSAGE_ID |
no | Thread the draft onto that message's conversation (see Threading). |
--thread THREAD_ID |
no | Attach the draft to a threadId directly, no header lookup. Prefer --reply-to. |
--attach PATH |
no | Attach a local file. Repeatable; composes with every other flag. |
What ships with it
3 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.
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 First seen · 345 lines · 48 tokens per session scan A a6dc2d7c8912
gmail-draft-from-markdown is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 4,146 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.