Borrowing it
Nothing to install: this file belongs to yukiyokotani/office-open-xml-viewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yukiyokotani/office-open-xml-viewer/main/AGENTS.mdgit clone --depth 1 https://github.com/yukiyokotani/office-open-xml-viewerWrote 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/instructions/yukiyokotani/office-open-xml-viewer/agents-md)<a href="https://agentmods.dev/instructions/yukiyokotani/office-open-xml-viewer/agents-md"><img src="https://agentmods.dev/badge/instructions/yukiyokotani/office-open-xml-viewer/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.
<a href="https://agentmods.dev/instructions/yukiyokotani/office-open-xml-viewer/agents-md"><img src="https://agentmods.dev/badge/instructions/yukiyokotani/office-open-xml-viewer/agents-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 | $0.05635 | $0.05635 |
| Opus 5.5 | $0.02254 | $0.02254 |
| Sonnet 5.5 | $0.01127 | $0.01127 |
| Haiku 4.5 | $0.00564 | $0.00564 |
Grade A, and why
office-open-xml-viewer 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 10d 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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This file is the canonical workflow for AI coding agents working on this
repository. Tool-specific files such as CLAUDE.md may add supplements, but they
must not contradict this file.
Project
office-open-xml-viewer renders OOXML documents (docx, xlsx, pptx) to
browser Canvas. The implementation is a Rust/WASM parser layer plus TypeScript
Canvas renderers and viewers.
Important directories:
packages/core/— shared rendering primitives and shared TypeScript helpers.packages/ooxml-common/— shared Rust parsing/model helpers.packages/docx/— DOCX parser, renderer, viewer, and tests.packages/xlsx/— XLSX parser, renderer, viewer, and tests.packages/pptx/— PPTX parser, renderer, viewer, and tests.site/— public site..storybook/— unified Storybook config.
Standard Development Flow
Use this flow for ordinary bug fixes and feature work:
-
Start from
mainand rungit pull --ff-only. -
If the checkout is dirty, preserve unrelated work before switching or pulling. Prefer
git stash push -u -m <clear-message>for work that appears to belong to another session. -
Create a feature branch. Use
codex/<topic>for Codex work when possible; otherwise follow the repository's existing branch naming. -
When creating or entering a Codex/Claude worktree, make the root checkout's ignored
spec/directory available from that worktree as a local symlink. For the standard.claude/worktrees/<name>layout, run:ln -s ../../../spec specIf the worktree lives elsewhere, create
specas a symlink to the main local checkout'sspec/directory. Do not copy or commit the specification files. -
Work with TDD for bug fixes:
- explore the failing sample or behavior,
- add a focused failing test,
- make it pass,
- refactor only where it reduces real complexity.
-
Verify with the narrowest meaningful tests first, then broader checks when the touched surface warrants it.
-
Commit only the intended source/docs/test files. Do not commit private samples or generated local artifacts.
-
Push the feature branch, create a PR, wait for checks when practical, and merge with a merge commit. Do not squash.
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.
- 10d ago Changed · +1 lines · +27 tokens per session 9d694f393167
- 12d ago Changed · +3 lines · +27 tokens per session 881ce682f2de
- 14d ago Changed · +8 lines · +118 tokens per session 8693d0797f41
- 1mo ago Changed · +45 lines · +631 tokens per session 4c1fe8b2b09e
- 1mo ago Changed · +58 lines · +737 tokens per session 1213f5719370
- 1mo ago Changed · +7 tokens per session 5676ec220bd8
- 1mo ago Changed · +50 lines · +676 tokens per session c7f54f2276b6
- 2mo ago First seen · 334 lines · 3,412 tokens per session scan A c05c41e2343a
office-open-xml-viewer AGENTS.md is an instructions file published in the GitHub repository yukiyokotani/office-open-xml-viewer (863 stars, last pushed yesterday), licensed MIT. It adds 5,635 tokens to every session, about $0.0225 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.
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).
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.
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).
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.
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).
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.