Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jtsternberg/claude-plugins/plugin install gwsWrote 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/md-to-google-doc)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/md-to-google-doc"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/md-to-google-doc/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/jtsternberg/claude-plugins/md-to-google-doc"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/md-to-google-doc.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 | $0.00032 | $0.03064 |
| Opus 5 | $0.00016 | $0.01532 |
| Sonnet 5 | $0.00006 | $0.00613 |
| Haiku 4.5 | $0.00003 | $0.00306 |
Grade A, and why
md-to-google-doc 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 9d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown to Google Doc
Upload local markdown files to Google Drive as formatted Google Docs. The best available path depends on which account can authenticate and how much fidelity the target doc needs.
Source routing
gws only authenticates your personal Google account. If the target doc's
account isn't reachable by gws, route through the next rung — try in
order, and only read/run the next rung's setup on fallthrough.
Rung 1 — gws (default, unchanged)
Use the existing workflow below: full create, update-in-place, tab
management, section linking. This is the primary path whenever gws can
authenticate to the target account.
Fall through to rung 2 if gws auth status fails or the target account
can't reach the destination folder/doc (403/404 for that account, not an
expired-token case).
Rung 2 — gcloud ADC (create + update-in-place, for accounts gws can't reach)
Direct Drive/Docs API access via ADC. Supports create (files.create with
a markdown upload — same server-side importer gws uses) and
update-in-place: a state file
(~/.config/gws-md-to-gdoc/rendered.json) remembers which source file
produced which doc ID, so reruns update instead of duplicating. Sets
PAGELESS via a batchUpdate after create, same as gws.
# Codex: this path resolves under Claude Code; substitute the directory containing this SKILL.md.
SKILL_DIR="${CLAUDE_SKILL_DIR}"
bash "$SKILL_DIR/scripts/adc-check.sh" # fast preflight; exit 0 = configured
bash "$SKILL_DIR/scripts/adc-create.sh" <file.md> [folder-id-or-url] [--title "Title"] [--new]
--new forces a fresh doc even if the state file has a prior entry for this
source file. If adc-check.sh fails, it prints an actionable one-line
reason — only then read
references/adc-setup.md for the full gcloud
setup steps. If ADC isn't configured and setting it up isn't worth it right
now, fall through to rung 3.
Not supported on this rung yet: tab-scoped publishing, section linking (both gws-only for now).
What ships with it
22 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.
- agents/openai.yaml 160 B
- references/adc-setup.md 2.7 KB
- references/MANUAL.md 1.2 KB
- scripts/adc_create.py 7.7 KB runs code
- scripts/adc_state.py 1.9 KB runs code
- scripts/adc-check.sh 813 B runs code
- scripts/adc-create.sh 2.3 KB runs code
- scripts/clean.sh 481 B runs code
- scripts/gdoc.sh 1.4 KB runs code
- scripts/link_sections.py 3.7 KB runs code
- scripts/link-sections.sh 2.4 KB runs code
- scripts/replay_tab.py 12 KB runs code
- scripts/tab-update.sh 5.4 KB runs code
- scripts/tabs.sh 4.5 KB runs code
- scripts/update.sh 3.7 KB runs code
- scripts/upload.sh 4.7 KB runs code
- tests/fixtures/tab-fixture.md 268 B
- tests/smoke-tabs.sh 4.4 KB runs code
- tests/test_adc_create.py 7.3 KB runs code
- tests/test_adc_state.py 2.2 KB runs code
- tests/test_link_sections.py 2.9 KB runs code
- tests/test_replay_tab.py 13 KB runs code
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.
- 9d ago First seen · 285 lines · 32 tokens per session scan A 9786daf2668c
md-to-google-doc is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 3,064 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…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.