office-open: Instructions file for Codex

AGENTS.md

office-open AGENTS.md is an instructions file for Codex, OpenCode from DemoMacro/office-open. It costs 3,462 tokens per session, scanned A, a copy of office-open CLAUDE.md, MIT.

Project instructions for office-open, a TypeScript library that reads and writes Word, PowerPoint, and Excel document files. A monorepo is one repository containing multiple related packages.

In plain words
What is it for?
Use them when developing or maintaining the library's DOCX, PPTX, and XLSX parsing, writing, and shared TypeScript code.
Why use it?
They explain the project's package layout and shared patterns so changes to document parsing and generation fit the existing design.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is DemoMacro/office-open's own configuration. It tells Codex and OpenCode how to work on office-open 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 office-open configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DemoMacro/office-open. 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/DemoMacro/office-open/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/DemoMacro/office-open

Made for: Codex, OpenCode.

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 office-open AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/demomacro/office-open/agents-md/github.svg)](https://agentmods.dev/instructions/demomacro/office-open/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/demomacro/office-open/agents-md"><img src="https://agentmods.dev/badge/instructions/demomacro/office-open/agents-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 office-open AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/demomacro/office-open/agents-md"><img src="https://agentmods.dev/badge/instructions/demomacro/office-open/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,462 This file is loaded in full into every session.
When invoked 3,462 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 100% copy Near-identical to another mod 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 $0.03462 $0.03462
Opus 5.5 $0.01385 $0.01385
Sonnet 5.5 $0.00692 $0.00692
Haiku 4.5 $0.00346 $0.00346

Measured 3d ago against content hash 8aea511e4c7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

office-open AGENTS.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 3d 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.

Origin

This is a copy

100% identical to office-open CLAUDE.md — 60 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior TypeScript developer.

Project

office-open is a monorepo for generating and parsing Office Open XML documents (.docx, .pptx, .xlsx) with JS/TS. Declarative API, works in Node.js and browsers. Bidirectional: stringify (JSON → XML) and parse (XML → JSON).

Architecture

  • Packages: core/ (shared OOXML domains — descriptor runtime, drawing/, chart/, table/, picture/, connector/, group/, smartart, OPC), xml/, docx/, pptx/, xlsx/, legacy readers doc/, xls/, ppt/, rtf/, and ODF codecs odf/, odt/, ods/, odp/. OOXML format packages are peers: same src/ layout (parts/, shared/, compiler.ts, context.ts, generate.ts, parse.ts, patch.ts, index.ts) and one **Options name per shared concept.
  • Parts: one module per OOXML XML part. docx/xlsx co-locate types and the <part>Desc descriptor; pptx keeps descriptors in parts/descriptors/ with public types in shared/<domain>/. Cross-part shared types live in shared/.
  • Descriptor pattern: every part is a CustomDescriptor<T> with hand-written stringify(opts, ctx) + parse(el, ctx) (bidirectional). Runtime at packages/core/src/descriptor/.
  • Cross-format copy reuses core's shared domains + package-to-package conversion in packages/office-open/src/convert/ — no unified document-model layer. The conversion mode follows how the concept's XML maps across packages:
    • Identical XML (chart: one c:chartSpace part) → shared core model, no conversion.
    • Same element, different anchoring (picture pic:pic/p:pic/xdr:pic; shapes; text) → each package owns an *Options reflecting its anchor model (docx wp:inline/wp:anchor, pptx spTree, xlsx cell anchor) + pairwise convert/* functions; N is small, so pairwise beats a hub-spoke intermediate. The shared payload still lands in core: core/picture/ BasePictureOptions (data/type + cNvPr via NonVisualDrawingPropertiesOptions) is extended by pptx/xlsx PictureOptions, while docx stays a format discriminated union bridged through its altText; convert/picture.ts threads the cNvPr fields (name/description/title/hidden) straight through every leg. The same NonVisualDrawingPropertiesOptions (a:CT_NonVisualDrawingProps) backs every drawing's cNvPr/docPr across all three packages via core/drawing/non-visual/.
    • Structurally different XML (table: w:tbl flow / a:tbl graphic / sml cell-range) → core/table/ defines the shared structural base (BaseTableOptions/BaseTableRowOptions/BaseTableCellOptions: rows/cells/span/6-flags/columnWidths/vertical-align); docx/pptx TableOptions extends Base* add domain-specific style/position, xlsx is independent (its sml Table is a data range, restored visually via convert/table.ts). convert/table.ts passes the structural base through directly and translates only cell content (w:p↔a:p via convert/text), units (twip↔EMU via core/util/converters), and pptx fill/scheme-color → docx shading/themeColor.
    • Connector (cxnSp: p:cxnSp/xdr:cxnSp; docx has no standalone cxnSp) → core/connector/ BaseConnectorOptions extends NonVisualDrawingPropertiesOptions (cNvPr + locking + start/end connection endpoints; no spPr — pptx top-level convenience vs xlsx spPr asymmetry, kept per-package). pptx ConnectorOptions/LineShapeOptions and xlsx ConnectorOptions extend base; convert/connector.ts threads cNvPr + locking + endpoints via pickConnectorBase.
    • Group (grpSp: p:grpSp/xdr:grpSp/wpg:wgp) → core/drawing/group-shape-properties-desc.ts GroupShapePropertiesOptions (CT_GroupShapeProperties: xfrm/fill/effects/scene3d — no geometry/ln/sp3d, distinct from CT_ShapeProperties) + core/group/ BaseGroupOptions extends NonVisualDrawingPropertiesOptions (cNvPr only; grpSpPr content/children/position stay per-package). pptx/xlsx/docx all use GroupOptions (docx bridged through altText like picture). convert/group.ts threads container + child cNvPr via pickGroupBase/pickNonVisualDrawingProperties.
    • Shape base is YAGNI: cNvPr is already unified via NonVisualDrawingPropertiesOptions (Phase 2), spPr/textBody already live in core, there are no scattered convert adapters and no shape-specific public field worth lifting — so no BaseShapeOptions is introduced.
  • OOXML XSD (ooxml-schemas/transitional/) is the golden source of truth — wml.xsd (DOCX), pml.xsd (PPTX), sml.xsd (XLSX), dml-main.xsd (DrawingML). Validate XML output against it.

Read the full file on GitHub · 60 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. 3d ago Changed · +41 tokens per session 8aea511e4c7f
  2. 15d ago Changed · +1 lines · +72 tokens per session e0f16ce810cd
  3. 20d ago Changed · -1 tokens per session ce9c64945c25
  4. 27d ago First seen · 59 lines · 3,350 tokens per session scan A ba212a086c21

Subscribe to this mod's changes

office-open AGENTS.md is an instructions file published in the GitHub repository DemoMacro/office-open (38 stars, last pushed today), licensed MIT. It adds 3,462 tokens to every session, about $0.0138 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to office-open CLAUDE.md, differing in 60 lines, and is treated as a copy.

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 · 7,581 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

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens