adeu: Instructions file for Gemini CLI

GEMINI.md

adeu GEMINI.md is an instructions file for Gemini CLI from dealfluence/adeu. It costs 1,142 tokens per session, scanned A, original, MIT.

Instructions for using Adeu, a document tool that reads and edits Microsoft Word files with native tracked changes for AI-assisted revisions.

In plain words
What is it for?
Use it to read documents in clean or outline form, inspect defined terms and form fields, search for text, and apply revisions that remain visible in Word.
Why use it?
It provides a structured way to understand document text, insertions, deletions, comments, fields, headings, and legal cross-references before making edits.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is dealfluence/adeu's own configuration. It tells Gemini CLI how to work on adeu 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 adeu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dealfluence/adeu. 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/dealfluence/adeu/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/dealfluence/adeu

Made for: Gemini CLI.

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 adeu GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dealfluence/adeu/gemini-md/github.svg)](https://agentmods.dev/instructions/dealfluence/adeu/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/dealfluence/adeu/gemini-md"><img src="https://agentmods.dev/badge/instructions/dealfluence/adeu/gemini-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.

agentmods 80×15 button for adeu GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dealfluence/adeu/gemini-md"><img src="https://agentmods.dev/badge/instructions/dealfluence/adeu/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,142 This file is loaded in full into every session.
When invoked 1,142 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01142 $0.01142
Opus 5.5 $0.00457 $0.00457
Sonnet 5.5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2mo ago against content hash 5778ff673ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adeu GEMINI.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 2mo 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.

GEMINI.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adeu — Native Track Changes for AI

Adeu is your document redlining engine. It gives you a safe, token-efficient interface to read and edit .docx files, producing native Microsoft Word Track Changes rather than rewriting the file.

Available Tools

read_docx

Reads a DOCX file and returns its content as CriticMarkup-annotated text:

  • {++inserted++} — tracked insertion
  • {--deleted--} — tracked deletion
  • {>>comment<<} — comment

Key parameters:

  • file_path (required): absolute path to the .docx file
  • clean_view=true: returns the accepted/final text with no markup — use this first to understand context
  • mode="outline": returns a heading map only — start here on large documents before reading in full
  • mode="appendix": returns defined terms and cross-reference anchors — consult before editing legal docs
  • mode="fields": returns a ledger of all form fields (content controls) with CC: ID, tag, alias, type, state, and options
  • fields_offset=N: 0-indexed pagination offset for mode="fields"
  • page=N: navigate paginated full-text output
  • search_query="text": search document for specific text matches
  • max_matches=N: cap number of search matches returned (default 20)
  • match_offset=N: 0-indexed pagination offset for search matches
  • full_paragraph=true: expand search match snippets to complete paragraphs
  • force=true: bypass whole-document token budget guard refusal for large files

process_document_batch

Applies a list of edits to a DOCX. Edits apply sequentially — each one evaluates against the document state produced by the edits before it, so dependent edits may be chained in one batch (a later edit must target the text as it reads after the earlier edits). By default (partial=true), valid edits apply while failing edits return detailed error reports; set partial=false for transactional rollback if any edit fails validation.

Key parameters:

  • file_path (required): absolute path to the .docx file
  • changes (required): list of change objects
  • partial=true (default true): non-transactional batch execution — valid edits apply while failing edits return detailed error reports. Pass partial=false for transactional rollback if any edit fails validation.
  • ignore_control_locks=true: permit writes to content-locked controls (sdtContentLocked)
  • ignore_document_protection=true: permit writes to read-only or comments-protected documents
  • allow_untracked_writes=true: permit writes in fill-in-forms protected documents (where Word suppresses change tracking)

Read the full file on GitHub · 65 lines

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. 2mo ago First seen · 65 lines · 1,142 tokens per session scan A 5778ff673ca6

Subscribe to this mod's changes

adeu GEMINI.md is an instructions file published in the GitHub repository dealfluence/adeu (169 stars, last pushed 3d ago), licensed MIT. It adds 1,142 tokens to every session, about $0.0046 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens