rdocx: Instructions file for Claude Code

CLAUDE.md

rdocx CLAUDE.md is an instructions file for Claude Code from tensorbee/rdocx. It costs 2,248 tokens per session, scanned A, original, MIT.

Repository instructions for rdocx, a Rust workspace that handles Office Open XML documents such as word-processing and presentation files.

In plain words
What is it for?
Use them to orient an agent working on the rdocx codebase and its Rust packages.
Why use it?
They give a coding agent the project background, required reading, layout, and build and test expectations before it changes the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Codex.

This is tensorbee/rdocx's own configuration. It tells Claude Code how to work on rdocx 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 rdocx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tensorbee/rdocx. 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/tensorbee/rdocx/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tensorbee/rdocx

Made for: Claude Code.

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 rdocx CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tensorbee/rdocx/claude-md"><img src="https://agentmods.dev/badge/instructions/tensorbee/rdocx/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,248 This file is loaded in full into every session.
When invoked 2,248 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 $0.02248 $0.02248
Opus 5.5 $0.00899 $0.00899
Sonnet 5.5 $0.00450 $0.00450
Haiku 4.5 $0.00225 $0.00225

Measured 2d ago against content hash bc4ffaa5e0a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rdocx CLAUDE.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 2d 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.

CLAUDE.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for coding agents working in this repository.

.claude/WORKFLOW.md wins on any process question. This file describes the repository. That one describes how work lands in it.

What this repo is

A Rust workspace for Office Open XML. Three families of crates:

  • oxml-*, format-neutral OOXML infrastructure. The OPC container, units, DrawingML, image handling, layout primitives, the PDF backend.
  • rdocx-*, WordprocessingML. A shipped port of python-docx, prepared at 0.16.4 across the exact seven-package stable family and Python distribution. The previous complete family release was 0.16.3. The immutable v0.11.0 attempt published only rdocx-opc and rdocx-oxml. Historical releases remain available.
  • rpptx-*, PresentationML. A port of python-pptx, under construction.

The repository is named rdocx for historical reasons and keeps that name deliberately: renaming it would buy a more accurate name and cost a redirect that breaks the moment anything is created at the old path.

Read docs/hld/00-vision.md first, then 03-architecture.md.

Read first

  • Every compile and test task runs natively. There is no dev container.
  • The hash harness gates every PR in M1 through M6. An unexplained output delta blocks the merge. Never fold a behaviour change into a file move.
  • Rendering baselines require deterministic font mode. System fonts differ between machines, so a baseline recorded against them is worthless.
  • No em-dash, no prose semicolon in tracked Markdown or commit messages.
  • Never Co-Authored-By.

Layout

Path What
crates/oxml-* Format-neutral infrastructure. Must not depend on rdocx-* or rpptx-*. No exceptions: the Theme adapter lives in rdocx-oxml, so that edge runs rdocx-oxml -> oxml-drawing
crates/rdocx-* WordprocessingML. rdocx-oxml holds the w: types, rdocx-layout the flow engine and paginator, rdocx the facade
crates/rpptx-* PresentationML. rpptx-oxml the p: types, rpptx-layout the inheritance resolver, rpptx-render the slide renderer, rpptx the facade
crates/oxml-layout/fonts/ 32 bundled TTFs compiled unconditionally. The optional system-fonts feature adds host discovery. Every family needs a licence file
crates/rpptx/assets/ The bundled default.pptx. Must live under the crate directory or it is not in the published tarball
docs/hld/ The spec set, 00 to 15. Precedence rule in docs/hld/README.md
docs/sprints/ BACKLOG, SPRINT_PLAN, CURRENT_SPRINT, SPRINT_TRACKER, AS_BUILT
.claude/ WORKFLOW.md, commands/, skills/, design plans, reviews, worker handoffs
.agents/skills/ Generated Codex adapters for the same commands and skills. Never hand-edited. scripts/sync_agent_skills.py owns them
samples/ Generated output, gitignored. Regenerated by an example, not a fixture source
scripts/ Gate scripts and the sprint state machine
tools/gen-presets/ Offline generator for the preset shape table. Output is checked in

Read the full file on GitHub · 165 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. 2d ago Changed bc4ffaa5e0a6
  2. 6d ago Changed · +4 lines · +56 tokens per session 3af0d3d1a64e
  3. 11d ago Changed 4be6db9c18ed
  4. 13d ago Changed 271531ba98aa
  5. 14d ago Changed f34b003e4192
  6. 20d ago Changed c5a498a6a7d1
  7. 26d ago First seen · 161 lines · 2,192 tokens per session scan A 47435a617cea

Subscribe to this mod's changes

rdocx CLAUDE.md is an instructions file published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 2,248 tokens to every session, about $0.0090 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 2026-10-04.

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 · 2,750 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