gogcli: Skill for Codex

.agents/skills/gog-docs/SKILL.md

gog-docs is a skill for Codex from openclaw/gogcli. It costs 11 tokens per session (1,014 once invoked), scanned A, original, MIT.

A command-line tool for reading and editing Google Docs, including document text, tabs, tables, comments, and formatting.

In plain words
What is it for?
It helps create, copy, read, format, update, and manage the contents of Google Docs.
Why use it?
It lets coding agents work with Google Docs directly instead of requiring manual copy-and-paste through the browser.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is openclaw/gogcli's own configuration. It tells Codex how to work on gogcli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gogcli configures →

About the project

gog is a command-line client for Google Workspace services such as Gmail, Calendar, Drive, Docs, and Sheets. It is used by people, scripts, continuous-integration jobs, and coding agents that need account selection, structured output, and permission controls from a terminal.

openclaw/gogcli · 8,542 stars · on GitHub · gogcli.sh

Reuse

Borrowing it

Nothing to install: this file belongs to openclaw/gogcli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/openclaw/gogcli/main/.agents/skills/gog-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/openclaw/gogcli

Made for: Codex.

Wrote 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.

agentmods badge for gog-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/openclaw/gogcli/gog-docs/github.svg)](https://agentmods.dev/skills/openclaw/gogcli/gog-docs)
Your own site
<a href="https://agentmods.dev/skills/openclaw/gogcli/gog-docs"><img src="https://agentmods.dev/badge/skills/openclaw/gogcli/gog-docs/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.

agentmods 80×15 button for gog-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/openclaw/gogcli/gog-docs"><img src="https://agentmods.dev/badge/skills/openclaw/gogcli/gog-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.01014
Opus 5.5 $0.00004 $0.00406
Sonnet 5.5 $0.00002 $0.00203
Haiku 4.5 $0.00001 $0.00101

Measured 1mo ago against content hash 8569ae8380e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gog-docs 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 1mo 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.

.agents/skills/gog-docs/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Docs

Use gog for Google Docs operations. Read ../gog/SKILL.md first for shared auth, output, safety, and live-write rules.

Safe start

gog auth list --check --json --no-input
gog schema docs --json
gog --readonly --account [email protected] docs cat DOCUMENT_ID --json --wrap-untrusted
  • Select the account explicitly with --account.
  • Use --json --wrap-untrusted for agent-readable Google content.
  • Use --readonly when the task must not mutate Google data.
  • Use --no-input in automation and --dry-run before supported writes.
  • Confirm the exact account, object, and mutation before any write or delete.

Commands

Command Purpose
add-tab Add a tab to a Google Doc
cat Print a Google Doc as plain text
cell-style Apply table cell, border, padding, alignment, and text styling
cell-update Replace or append content inside a specific table cell
clear Clear all content from a Google Doc
comments Manage comments on files
copy Copy a Google Doc
create Create a Google Doc
delete Delete text range from document
delete-tab Delete a tab from a Google Doc
edit Find and replace text in a Google Doc
export Export a Google Doc (pdf|docx|txt|md|html)
find-range Find text and print Docs API UTF-16 index ranges
find-replace Find and replace text. Supports plain text or markdown with images; use --first for a single occurrence.
footer List, create, or delete document footers
format Apply text or paragraph formatting to a Google Doc
header List, create, or delete document headers
headings List document headings
images List document images
info Get Google Doc metadata
insert Insert text at a specific position
insert-date-chip Insert a native date smart chip
insert-file-chip Insert a native Drive file smart chip
insert-footnote Insert and populate a footnote
insert-horizontal-rule Insert a paragraph-border horizontal rule
insert-image Insert a public image URL or upload a local image into a Google Doc
insert-page-break Insert a page break at a specific position (or end-of-doc with --at-end)
insert-person Insert a native person smart chip
insert-section-break Insert a continuous or next-page section break
insert-table Insert a native table at a specific position (or end-of-doc with --at-end), optionally populated via --values-json
list-tabs List all tabs in a Google Doc
named-range Manage named ranges
page-layout Set page layout (pageless|pages) on an existing Google Doc
paragraphs List document paragraphs
raw Dump raw Google Docs API response as JSON (Documents.Get; lossless; for scripting and LLM consumption)
rename-tab Rename a tab in a Google Doc
replace-image Replace an existing image without changing its position or bounds
section-columns Set the column count for a document section
sed Regex find/replace (sed-style: s/pattern/replacement/g)
structure Show document structure with numbered paragraphs
suggestions List pending text suggestions
table-column Insert or delete native table columns
table-column-width Set or reset native table column widths
table-merge Merge a native table cell range
table-row Insert, delete, style, or pin native table rows
table-unmerge Unmerge the region containing a native table cell
tables List native tables
tabs Manage Google Doc tabs
update Insert or replace text at a specific index or range in a Google Doc
write Write content to a Google Doc

Read the full file on GitHub · 84 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 1mo ago First seen · 84 lines · 11 tokens per session scan A 8569ae8380e4

Subscribe to this mod's changes

gog-docs is a skill published in the GitHub repository openclaw/gogcli (8,542 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,014 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.