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-review)<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/design-review"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/design-review/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/openplanr/planr-pipeline/design-review"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/design-review.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 | $0.00035 | $0.00538 |
| Opus 5 | $0.00017 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
design-review 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 10d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/planr-pipeline:design-review {slug}
Turns a /planr-pipeline:design artifact into a live review canvas: the board daemon
serves the real finalized.html / canvas.html, the user pins comments on exact regions
(each pin auto-maps to its screen/section id), and this loop regenerates only the pinned
screen — then the results flow back into the PO artifacts (design-spec.md,
finalized.json, .run-manifest.jsonl).
Engine: ${CLAUDE_PLUGIN_ROOT}/lib/design-engine/cli.mjs (absolute paths everywhere —
hard rule 6). R1: STOPS after approval; print next: /planr-pipeline:plan {slug}.
The board may be shared only through its explicit Share control (or an explicit
planr artifact share <artifact-file> command). Opening, commenting, regenerating, or
approving does not publish the artifact. A remote reviewer returns an immutable review URL;
planr artifact import "<returned-review-url>" deliberately merges that review into the
adjacent feedback lifecycle. Share/import never auto-chain this review into /plan or /ship.
Task tracking
Phase A — Locate artifact + serve review boardPhase B — Pin loop (regenerate pinned screens, lint-gated)Phase C — Approve + sync PO artifacts (R1 stop)
Execute
${CLAUDE_PLUGIN_ROOT}/procedures/design-review-loop.md — all three phases.
Non-negotiables
- The lint gate stays at 0 errors after every regeneration
(
node $PLUG/lib/design/lint.mjs <artifact>— off-grid spacing + AA contrast are hard failures; design-system token/font adherence warnings get fixed, not ignored). - Only the pinned screen/section is regenerated — never the whole artifact for one pin.
- Feedback is the board's FILE;
feedback-pending.jsonis consumed on read (hard rule 3). - AskUserQuestion is only the blocking wait; the board is where review happens (hard rule 2).
- Share and review-URL import require explicit user actions; neither is an approval signal, regeneration request, publication side effect, or PLAN → SHIP transition.
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.
- 10d ago First seen · 43 lines · 35 tokens per session scan A 151c9c0d0093
design-review is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 538 once invoked, about $0.0002 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.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.