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/google-doc-to-md)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/google-doc-to-md"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/google-doc-to-md/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/google-doc-to-md"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/google-doc-to-md.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 | $0.00031 | $0.02255 |
| Opus 5 | $0.00015 | $0.01128 |
| Sonnet 5 | $0.00006 | $0.00451 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
google-doc-to-md 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Doc to Markdown
Download Google Docs as local markdown files. The Google Drive API natively
supports text/markdown as an export format, so no external conversion
tools are needed — the only variable is which account can authenticate to
reach the doc.
Source routing
gws only authenticates your personal Google account. If the doc lives in
an account gws can't reach (e.g. a work account), route through the next
rung instead of giving up. Try rungs in order; only read/run the next rung
on fallthrough — don't front-load setup you may not need.
Rung 1 — gws (default, unchanged)
Use the existing workflow below. This is the primary path whenever gws
can authenticate to the doc's account.
Fall through to rung 2 if gws auth status fails, or the export/metadata
call 403s/404s for the doc (wrong account, not the auth-expired case —
that's a gws auth login fix, not a routing fallthrough).
Rung 2 — gcloud ADC (optional, only if configured)
Same clean native text/markdown export as rung 1 — same server-side
exporter — just authenticated via gcloud Application Default Credentials
instead of gws. Use this when the doc's account has ADC set up but not
gws (e.g. a work account you've done gcloud auth application-default login for).
# 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-export.sh" <doc-id-or-url> [output.md]
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 — don't load it up front. If ADC isn't configured and setting
it up isn't worth it right now, fall through to rung 3.
Escaping note (all rungs): Drive's native exporter also backslash-escapes markdown-significant punctuation that appears as literal text in the doc (
Catch up\!,\#123,(Q2 2026\)) — verified live 2026-07-16 on a real doc. It's valid CommonMark, but if the raw markdown is for human editing, the same de-escaper works on any rung. Codex: this path resolves under Claude Code; substitute the directory containing this SKILL.md inSKILL_DIR="${CLAUDE_SKILL_DIR}"; python3 "$SKILL_DIR/scripts/deescape.py" in.md out.md. Docs that round-tripped from markdown import export clean; docs with hand-typed punctuation don't. The connector rung always needs it.
What ships with it
12 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 155 B
- references/adc-setup.md 2.3 KB
- references/MANUAL.md 738 B
- scripts/adc_export.py 3.5 KB runs code
- scripts/adc-check.sh 813 B runs code
- scripts/adc-export.sh 477 B runs code
- scripts/deescape.py 2.6 KB runs code
- scripts/docjson_to_md.py 3.9 KB runs code
- scripts/download.sh 3.6 KB runs code
- tests/test_adc_export.py 2.7 KB runs code
- tests/test_deescape.py 4.2 KB runs code
- tests/test_docjson_to_md.py 2.6 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 · 218 lines · 31 tokens per session scan A 02419d6d0609
google-doc-to-md is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 2,255 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.