Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add openplanr/planr-pipeline/plugin install planr-pipelineWrote 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/openplanr/planr-pipeline/design)<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/design"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/design.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.02775 |
| Opus 5 | $0.00010 | $0.01388 |
| Sonnet 5 | $0.00004 | $0.00555 |
| Haiku 4.5 | $0.00002 | $0.00278 |
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 7d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/planr-pipeline:design {feature-name}
Generates a visual design artifact for {slug} and authors design-spec.md, so the
PO Phase decomposes real UI tasks. Run this before /planr-pipeline:plan — it is a
standalone command, not a step inside /plan (SPEC-015 finding A1). It never auto-chains
to /plan or /ship.
Three formats, one shared core:
| Format | What it is | Substrate |
|---|---|---|
| prototype | one interactive, self-contained screen | vanilla + Pretext |
| walkthrough | multi-screen gallery, grouped sidebar (anchor ≤8 / lazy >8 screens) | vanilla + Pretext |
| canvas | Figma-like pan/zoom board of artboards (export + view-only) | vendored React |
Flags
--format/--from— when both are supplied, the clarification prompt (Phase B) is skipped entirely → fully non-interactive (CI/headless), exactly like/ship --yes.--yes— auto-confirm overwrite/extract decisions (assume the recommended branch).--dry-run— resolve mode + design context + the recommended format, print the plan, and STOP (no generation, no writes). Fatal errors obeyfatal-error-format.md(two lines).
This command NEVER auto-chains. It stops after writing the artifact + design-spec.md.
A human reviews, then runs /planr-pipeline:plan {slug}. Enforced by
${CLAUDE_PLUGIN_ROOT}/docs/rules.md R1 (and the new design clause).
Review and sharing are explicit
Generation never publishes or uploads the design. The handoff may offer these optional, separate actions:
planr artifact <artifact-file> # local review only
planr artifact share <artifact-file> # explicit immutable share
planr artifact import "<returned-review-url>" # explicit feedback import
Opening or completing /design, approving locally, or continuing to /plan never invokes
artifact share. A remote reviewer returns a new review URL; importing it is also a deliberate
user action and does not start /plan or /ship.
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.
- 7d ago First seen · 181 lines · 21 tokens per session scan A 738d2126a948
design is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,775 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.
stark-director
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.
summary
Generate a consolidated project brief from design artifacts. For the full spec package with YAML specs and validation, use /compile instead.