Agentset is an open-source platform for building retrieval-augmented generation applications, which let AI systems find relevant information from document collections before generating responses. Developers use it for ingestion, vector search, evaluation, cited chat, hosting, and agentic applications through APIs and SDKs. Its catalogue rules and skills provide agent guidance for working with Agentset.
Borrowing it
Nothing to install: this file belongs to agentset-ai/agentset. 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/agentset-ai/agentset/main/.agents/skills/fixing-accessibility/SKILL.mdgit clone --depth 1 https://github.com/agentset-ai/agentsetWrote 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/agentset-ai/agentset/fixing-accessibility)<a href="https://agentmods.dev/skills/agentset-ai/agentset/fixing-accessibility"><img src="https://agentmods.dev/badge/skills/agentset-ai/agentset/fixing-accessibility/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/agentset-ai/agentset/fixing-accessibility"><img src="https://agentmods.dev/badge/skills/agentset-ai/agentset/fixing-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00009 | $0.00850 |
| Opus 5.5 | $0.00004 | $0.00340 |
| Sonnet 5.5 | $0.00002 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
fixing-accessibility 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- fixing-accessibility — 94% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fixing-accessibility
Fix accessibility issues.
how to use
-
/fixing-accessibilityApply these constraints to any UI work in this conversation. -
/fixing-accessibility <file>Review the file against all rules below and report:- violations (quote the exact line or snippet)
- why it matters (one short sentence)
- a concrete fix (code-level suggestion)
Do not rewrite large parts of the UI. Prefer minimal, targeted fixes.
when to apply
Reference these guidelines when:
- adding or changing buttons, links, inputs, menus, dialogs, tabs, dropdowns
- building forms, validation, error states, helper text
- implementing keyboard shortcuts or custom interactions
- working on focus states, focus trapping, or modal behavior
- rendering icon-only controls
- adding hover-only interactions or hidden content
rule categories by priority
| priority | category | impact |
|---|---|---|
| 1 | accessible names | critical |
| 2 | keyboard access | critical |
| 3 | focus and dialogs | critical |
| 4 | semantics | high |
| 5 | forms and errors | high |
| 6 | announcements | medium-high |
| 7 | contrast and states | medium |
| 8 | media and motion | low-medium |
| 9 | tool boundaries | critical |
quick reference
1. accessible names (critical)
- every interactive control must have an accessible name
- icon-only buttons must have aria-label or aria-labelledby
- every input, select, and textarea must be labeled
- links must have meaningful text (no “click here”)
- decorative icons must be aria-hidden
2. keyboard access (critical)
- do not use div or span as buttons without full keyboard support
- all interactive elements must be reachable by Tab
- focus must be visible for keyboard users
- do not use tabindex greater than 0
- Escape must close dialogs or overlays when applicable
3. focus and dialogs (critical)
- modals must trap focus while open
- restore focus to the trigger on close
- set initial focus inside dialogs
- opening a dialog should not scroll the page unexpectedly
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.
- 1mo ago First seen · 120 lines · 9 tokens per session scan A 94bfcccdf700
fixing-accessibility is a skill published in the GitHub repository agentset-ai/agentset (2,112 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 850 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…
autorag-setup
Install and configure AutoRAG, register its Lite MCP server for external agents, or repair its single search model, approved roots, indexes, datasources, and health checks without exposing credentials. Use when AutoRAG or MCP is missing, init/refresh/health fails, indexes are stale, or the user wants to add folders or…
autorag-lite-setup
Install and register the model-free AutoRAG Lite MCP server, configure approved roots and datasources, build indexes, and verify MCP discovery and search. Use when autorag-mcp is missing, MCP connection fails, indexes are stale, or the user wants document search without configuring a search model.
director-review
A review process for checking video prompts and generated images against story, action, camera, setting, timing, and continuity requirements. It requires visual evidence before declaring an image or sequence correct.
github-anime-aesthetics
A visual guide for animated scenes that keeps character shapes, clothing, colors, poses, and movement readable and consistent.