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/.claude/commands/study-crate.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/commands/tensorbee/rdocx/study-crate)<a href="https://agentmods.dev/commands/tensorbee/rdocx/study-crate"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/study-crate/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/commands/tensorbee/rdocx/study-crate"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/study-crate.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 | $0.00014 | $0.00611 |
| Opus 5.5 | $0.00006 | $0.00244 |
| Sonnet 5.5 | $0.00003 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
study-crate 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 26d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/study-crate
Produce a map of a crate: what it owns, what it depends on, where its seams are, and where its traps are. Read-only.
Use before the first story that touches an unfamiliar crate, or before an
XL story that will be split.
Steps
-
The manifest. Dependencies, features and their defaults, and anything unusual: a narrowed feature set, an
include, apublish = false. The rootCargo.tomlcarries comments explaining why several feature sets are minimal. Read them rather than regenerating the reasoning. -
The module tree. Every file with a one-line purpose and a line count. The line counts matter, because they say where the weight is.
-
The public surface. Everything re-exported from
lib.rs. Then, separately, types that leak: public function signatures naming a type from another crate that this crate does not re-export.rdocxhas several, and they turn an apparently internal change into a breaking one. -
The dependency position. What depends on this crate, and what it depends on. Confirm it respects the layering rule in
docs/hld/03-architecture.md. -
The conventions in force. How this crate parses and serialises, how it names things, how it handles errors, whether it captures raw XML. New code matches the file it sits in.
-
The traps. Anything a newcomer would get wrong:
- Behaviour that is deliberately wrong, listed in
CLAUDE.md. - Invariants held by convention rather than by the type system.
- Ordering requirements, such as OOXML
xsd:sequence. - Anything whose change moves the hash harness.
- Behaviour that is deliberately wrong, listed in
-
The tests. Where they live, what they cover, and what they do not. The gap is usually more useful than the coverage.
-
Report as a map. Do not paste large code blocks. Cite
path:lineand let the reader open it.
Report shape
# <crate>
**Purpose**: one sentence.
**Position**: depends on X, Y. Depended on by A, B.
**Size**: N files, N lines.
## Modules
| File | Lines | Purpose |
## Public surface
What is exported. What leaks and from where.
## Conventions
How this crate does things.
## Traps
Each with a path:line and why it bites.
## Test coverage
What is covered. **What is not.**
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.
- 26d ago First seen · 76 lines · 14 tokens per session scan A 13ab16f60a8b
study-crate is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 611 once invoked, about $0.0001 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 commands, from other repositories
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
start-0-8
A Japanese-language command that displays the current project setup progress.
setup-m365cli.es
Lesson command — Setup de M365 CLI.
prep-role
Deep prep for a specific role's interview process. The user wants to know what to expect, how to win, and what kills candidates at their level.
start-1
A guided beginner course for product managers learning Claude Code, a coding assistant that works from the command line.