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.
curl -O https://raw.githubusercontent.com/tensorbee/rdocx/main/AGENTS.mdgit clone --depth 1 https://github.com/tensorbee/rdocxWrote 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/tensorbee/rdocx/agents-md)<a href="https://agentmods.dev/instructions/tensorbee/rdocx/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorbee/rdocx/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/tensorbee/rdocx/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorbee/rdocx/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 | $0.02018 | $0.02018 |
| Opus 5.5 | $0.00807 | $0.00807 |
| Sonnet 5.5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
rdocx 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 6d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance for coding agents
This repository uses one development workflow across every agent and human
contributor. Before changing code or tracked documentation, read CLAUDE.md and
.claude/WORKFLOW.md. The workflow file wins on process questions.
Where the workflow lives
.claude/commands/<name>.md defines every command, and .claude/skills/<name>.md
holds the reference material those commands cite. Both are canonical for every
agent, whatever the directory is called.
Codex discovers the same set under .agents/skills/<name>/SKILL.md. Those are
generated adapters that point back at the canonical file with its SHA-256.
Never hand-edit one, and never treat one as the source. Regenerate with:
python3 scripts/sync_agent_skills.py # after editing any command or skill
python3 scripts/sync_agent_skills.py --check # drift gate, part of /verify
A generated adapter that has drifted from its source means the two agents are following different rules while believing they agree, which is why the check is a gate and not a warning.
Shared state
- Treat
docs/sprints/CURRENT_SPRINT.md,BACKLOG.md,SPRINT_PLAN.md,SPRINT_TRACKER.mdandAS_BUILT.mdas the shared delivery record. - Treat
.claude/plans/and.claude/reviews/as agent-neutral tracked artifacts despite the directory name. - Treat
.claude/scratch/F-XXX-progress.mdas the local in-flight record. Read it when resuming an in-progress F-ID, and update it before handing work over. - Treat
.claude/handoffs/F-XXX-ready.mdas the structured handoff a worker writes for the integrator./complete-feature --preparewrites it,scripts/sprint_workflow.py validate-handoffchecks it, and/integrate-featureconsumes and deletes it. - Never create a second sprint tracker, backlog, design plan or review record. There is exactly one of each.
Non-negotiable rules
- The hash harness gates every PR in M1 through M6. An unexplained output delta blocks the merge. Every intentional behavioural change is its own labelled commit with the expected delta stated and reviewed. Never fold a behaviour change into a file move.
- Rendering baselines use deterministic font mode. Never record a baseline against system fonts.
oxml-*crates must not depend onrdocx-*orrpptx-*, with the single documentedoxml-drawing -> rdocx-oxmlexception for theThemeadapter.- Preserve unmodelled XML verbatim. Parse only what you render.
- Respect schema child order. OOXML uses
xsd:sequence, and a violation makes PowerPoint refuse the file rather than warn. - Do not use em dashes or prose semicolons in tracked Markdown or commit messages.
- Do not run
cargo clean. Iterate scoped. - Do not commit or push unless the invoked workflow explicitly includes that action. Never add an agent co-author trailer.
- Only
/close-sprintmay merge tomainor create ansNNsprint tag. - Only
/releasemay create or push av*release tag or start crates.io publication. It requires a separate final approval at the reviewed SHA.
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.
- 6d ago Changed · +14 tokens per session 531e3611536f
- 11d ago Changed df1c2c129a57
- 26d ago First seen · 176 lines · 2,004 tokens per session scan A 9e454bb52b0f
rdocx AGENTS.md is an instructions file published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 2,018 tokens to every session, about $0.0081 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.
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).
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.