agentmods.dev

adeu AGENTS.md

Repository instructions for Adeu, a document engine that translates DOCX files and tracks edits in a structured representation, with Python and Node.js versions.

In plain words
What is it for?
Use them when working on the Python engine, TypeScript packages, MCP server, n8n integration, LangChain integration, desktop extension, or release scripts.
Why use it?
They explain the project’s monorepo, meaning one repository containing several related packages, and list the checks used to verify changes.

Instructions file for CodexOpenCode

149 2d ago A scan 1,774 tokens original MIT
View the source file dealfluence/adeu
Install

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.

agentmods
npx agentmods add instructions/dealfluence/adeu/agents-md
Clone the repo
git clone --depth 1 https://github.com/dealfluence/adeu

Made for: Codex, OpenCode.

Per session 1,774 This file is loaded in full into every session.
When invoked 1,774 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01774 $0.01774
Opus 5 $0.00887 $0.00887
Sonnet 5 $0.00355 $0.00355
Haiku 4.5 $0.00177 $0.00177

Measured yesterday against content hash 8e8441ab93f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adeu AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Test Subprocesses Decode Explicitly (python/):** `subprocess.run(..., text=True)` with no `encoding=` decodes with the host ANSI code page (cp1252 on Windows) while the CLI writes UTF-8 — and the resulting `UnicodeDe
AGENTS.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adeu Agent Instructions

Adeu is a DOCX ↔ LLM translation engine and redlining Virtual DOM. It maintains parallel Python and Node.js implementations plus a LangChain integration.

Repository Structure & Packages

  • python/: Core Python engine (adeu), FastMCP server (adeu-server), and CLI (adeu). Managed via uv (requires Python ≥ 3.12).
  • node/: Node.js workspace (requires Node ≥ 22.0.0).
    • node/packages/core: @adeu/core (TypeScript SDK & engine)
    • node/packages/mcp-server: @adeu/mcp-server (MCP server binary; builds extension bundle to desktop-extension/index.js)
    • node/packages/n8n-nodes-adeu: n8n-nodes-adeu (n8n community node)
  • langchain/: langchain-adeu integration package. Editable-links to python/ via tool.uv.sources.
  • desktop-extension/: Claude Desktop extension packaging (manifest.json + index.js).
  • scripts/: Monorepo automation (bump.py, check_release_consistency.mjs).

Commands & Verification Workflow

Run commands from the respective package directory:

Python (python/)

  1. Lint & Format Check: uv run ruff check . && uv run ruff format --check .
  2. Type Check: uv run mypy src
  3. Run Tests: uv run pytest
    • Single test: uv run pytest tests/test_engine.py -k "test_name"
    • Property tests (extended): uv run pytest --hypothesis-profile=hunt
    • Debug serial run: uv run pytest -n 0

Node.js (node/)

  1. Install: npm ci (not npm install: the split TypeScript pin below only holds if the tree matches the lockfile)
  2. Build All Packages: npm run build (MUST build before testing; compiles tsup outputs for all packages and verifies MCP bundle)
  3. Run Tests: npm run test
    • Single test: cd packages/core && npm run test -- -t "test_name"
  4. Lint: npm run lint (all workspaces), or cd packages/n8n-nodes-adeu && npm run lint

LangChain (langchain/)

  1. Lint & Format Check: uv run ruff check . && uv run ruff format --check .
  2. Type Check: uv run mypy langchain_adeu
  3. Run Tests: uv run pytest (single test: uv run pytest tests/unit_tests/test_apply_changes.py)

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 1,774 tokens per session scan A 8e8441ab93f8

Subscribe to this mod's changes

adeu AGENTS.md is an instructions file published in the GitHub repository dealfluence/adeu (149 stars, last pushed 2d ago), licensed MIT. It adds 1,774 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AIGit and workflowLocalizationai-agentsdocument-automationdocx-converterlegaltechllm-toolsmcp-server
Related

Other instructions, from other repositories

obsidian-wiki AGENTS.md

AGENTS.md instructions for Ar9av/obsidian-wiki, covering obsidian wiki — agent context, readme translation parity, configuration, targeting a specific vault and vault structure.

Ar9av/obsidian-wiki · 3,876 tokens

openscreen AGENTS.md

Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.

getopenscreen/openscreen · 5,627 tokens

spec-kit-zh AGENTS.md

Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.

loulanyue/spec-kit-zh · 3,968 tokens

GameDesignOS AGENTS.md

Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.

DY-2026/GameDesignOS · 972 tokens

open-dictionary AGENTS.md

Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.

ahpxex/open-dictionary · 1,906 tokens

openings-mcp AGENTS.md

Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.

amikai/openings-mcp · 99 tokens