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-brandkitgit 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-brandkit)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-brandkit"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-brandkit/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-brandkit"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/anti-slop-brandkit.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 | $0.00097 | $0.01245 |
| Opus 5.5 | $0.00039 | $0.00498 |
| Sonnet 5.5 | $0.00019 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
anti-slop-brandkit 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anti-slop-brandkit
A site with no brand gets a generic one by default: purple gradient, Inter, a letter-in-a-circle logo. This skill proposes a deliberate starting identity instead. The output is a proposal: a board image plus a written brief that the user approves before anything enters the project.
Authority: advisory. Findings feed the frontend-mockup-loop FIX step and never override a WCAG-AA or severity gate. A proposed palette that fails AA contrast is fixed in the brief, not defended.
When it applies
All of these must hold, otherwise generate nothing:
- The declared profile (
anti-slop-frontendDesign Read) isnew-site. - The project has no existing brand assets (logo, palette, type). With a
brand, use
anti-slop-redesigninstead. - Explicit request: the user asked for a brand kit / board.
- The user confirmed the plan in step 1.
Proposal, not identity
- Never write brand values into project tokens or UI contracts before the user
approves
brand.md. Output lands in the mockup folder only. - After approval, frontend-mockup-loop CONTRACT (
init_ui_contract) adopts the values; this skill never edits token files itself. - Logos are labelled concepts, never final marks. The board and
brand.mdboth say "logo concept".
Procedure
Image generation uses the same runner, backends, headless rule and fallback
as anti-slop-image-direction (read its "Images are experimental" section for
how to resolve $NB).
1. Plan, then confirm
- Resolve
<mockupDir>exactly asanti-slop-image-directiondoes. - Write the strategy first, in three lines: what the product does, for whom, and the one feeling the brand must carry.
- Confirm with
ask_user, stating: the image count (1 board unless the user asks for variants), the backend (geminiorpi), and that generation is paid. No confirmation → generate nothing. - A backend change requires a new confirmation; never switch the backend silently.
- Headless rule: if the
ask_usertool is absent from your tool list, the run is headless: generate nothing and write the text-only brief.
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 · 117 lines · 97 tokens per session scan A 4a33bf245def
anti-slop-brandkit is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,245 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.