Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill anti-slop-redesigngit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-redesign)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-redesign"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-redesign/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/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-redesign"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-redesign.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 | $0.00088 | $0.01361 |
| Opus 5.5 | $0.00035 | $0.00544 |
| Sonnet 5.5 | $0.00018 | $0.00272 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
anti-slop-redesign 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 5d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anti-slop-redesign
Most UI work changes a surface that already ships. Misclassifying the mode is the biggest source of bad redesign output: a "refresh" that renames routes, breaks e2e selectors and drops keyboard shortcuts is a regression, however good it looks. This skill makes the mode, the audit and the protected list explicit before anything is touched.
Authority: advisory. Findings feed the frontend-mockup-loop FIX step and
never override a WCAG-AA or severity gate. When a recommendation conflicts
with a gate result, the gate result stands and the recommendation is recorded
as overridden. The tell catalog itself lives in anti-slop-frontend; this
skill decides what may change and in which order.
When to Use
- A request to redesign, modernise, refresh or de-template an existing surface.
- Before
frontend-mockup-loopMOCKUP on any surface that already ships. - Not for a site with no shipped design: that is
new-site→greenfield.
Procedure
1. Declare the mode (before any edit)
State the anti-slop-frontend Design Read, then one of three modes:
| Mode | Means |
|---|---|
greenfield |
no existing design, or a full rebuild was explicitly approved |
preserve |
modernise without breaking brand, IA, copy voice or hooks |
overhaul |
new visual language on the existing content and IA |
Defaults per surface profile:
| Profile | Default mode |
|---|---|
product-ui |
preserve |
marketing |
preserve |
new-site |
greenfield |
overhaulrequires explicit user confirmation before proceeding. Ask once (ask_userwhen available); without a yes, stay inpreserve.- Pick
overhaulonly when the visual debt is structural (no design system, broken mobile, broken IA). Sound IA and content →preserve.
2. Audit before edit
Produce the audit before touching any file. A redesign whose first artifact is a diff fails Verification.
- Screenshot of the current surface (both modes if the project ships both).
- Brand tokens in use: colour tokens, type stack, radius scale, logo.
- Tells found: run the
anti-slop-frontendchecklist for the declared profile; list each hit with its rule id (A3, B2, ...). - Missing states: loading / empty / error that do not exist yet.
- Protected inventory: list the items from "Never change silently" that
the surface contains (routes, nav labels, field names, shortcuts,
data-testidvalues). - Dial reading of the existing surface. That is the starting point, not a baseline.
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.
- 5d ago First seen · 133 lines · 88 tokens per session scan A eb39e275848d
anti-slop-redesign is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,361 once invoked, about $0.0004 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 2026-10-11.
Other skills, from other repositories
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.