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/design.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/design)<a href="https://agentmods.dev/commands/tensorbee/rdocx/design"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/design/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/design"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/design.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 | $0.00015 | $0.03501 |
| Opus 5.5 | $0.00006 | $0.01400 |
| Sonnet 5.5 | $0.00003 | $0.00700 |
| Haiku 4.5 | $0.00002 | $0.00350 |
Grade A, and why
design 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design F-XXX [--revise] [--draft]
Write .claude/plans/F-XXX-design.md. No code changes in this command.
The plan is a machine-consumed contract: /start-feature reads its test plan
and refuses a vague spec reference, and /complete-feature executes against its
HLD impact list. Write it as something that will be acted on, not as prose.
--draft is the mode /run-sprint uses to plan a whole sprint before
implementing any of it. It runs every step except interactive questioning in 4
and approval in 7, always writes the plan in 6, records open
questions instead of asking them, and leaves the status at draft. A plan left
at draft cannot be started.
Steps
-
Read the story. Find
### F-XXXindocs/hld/14-development-backlog.md. Take its size, dependencies and test gate verbatim. If the F-ID is not there, stop and say so. -
Read the cited spec sections. Follow the story into
docs/hld/and read the specific sections it implements. Read the actual code it will touch. Do not design from the backlog entry alone. -
Check dependencies. Record actual status from
docs/sprints/BACKLOG.md. Drafting may use a pending in-sprint provider's proposed contract, with its assumptions and readiness explicitly pending. Approve dependent designs in topological order only after their provider contracts are approved. Approval is not implementation readiness./start-featureand/claim-featurestill require dependencies to be actually done, including any required dependency-prefix checkpoint. An unfinished external dependency remains a named blocker. -
Ask before writing. Collect every open question and ask them in one round using AskUserQuestion. Questions where a wrong guess would mean rewriting the story are blocking. Everything else gets a stated assumption.
Under
--draft, skip this. Write the questions into## Open questionsand carry on, so a sprint's worth of planning produces one consolidated round of questions rather than one per story.
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 · +185 lines 4200a5757cdd
- 11d ago Changed · +4 lines 8af5b9adc5b4
- 26d ago First seen · 122 lines · 15 tokens per session scan A 6919a3896965
design is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 3,501 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
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.