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.
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 agentmods add skills/agentset-ai/agentset/fixing-metadatanpx skills add agentset-ai/agentset --skill fixing-metadatagit 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-metadata)<a href="https://agentmods.dev/skills/agentset-ai/agentset/fixing-metadata"><img src="https://agentmods.dev/badge/skills/agentset-ai/agentset/fixing-metadata.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 | $0.00011 | $0.00889 |
| Opus 5 | $0.00005 | $0.00445 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
fixing-metadata 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 6d 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-metadata — 86% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fixing-metadata
Ship correct, complete metadata.
how to use
-
/fixing-metadataApply these constraints to any metadata work in this conversation. -
/fixing-metadata <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 introduce new frameworks or SEO libraries unless explicitly requested. Prefer minimal diffs.
when to apply
Reference these guidelines when:
- adding or changing page titles, descriptions, canonical, robots
- implementing Open Graph or Twitter card metadata
- setting favicons, app icons, manifest, theme-color
- building shared SEO components or layout metadata defaults
- adding structured data (JSON-LD)
- changing locale, alternate languages, or canonical routing
- shipping new pages, marketing pages, or shareable links
rule categories by priority
| priority | category | impact |
|---|---|---|
| 1 | correctness and duplication | critical |
| 2 | title and description | high |
| 3 | canonical and indexing | high |
| 4 | social cards | high |
| 5 | icons and manifest | medium |
| 6 | structured data | medium |
| 7 | locale and alternates | low-medium |
| 8 | tool boundaries | critical |
quick reference
1. correctness and duplication (critical)
- define metadata in one place per page, avoid competing systems
- do not emit duplicate title, description, canonical, or robots tags
- metadata must be deterministic, no random or unstable values
- escape and sanitize any user-generated or dynamic strings
- every page must have safe defaults for title and description
2. title and description (high)
- every page must have a title
- use a consistent title format across the site
- keep titles short and readable, avoid stuffing
- shareable or searchable pages should have a meta description
- descriptions must be plain text, no markdown or quote spam
3. canonical and indexing (high)
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.
- 6d ago First seen · 116 lines · 11 tokens per session scan A 08b706369e90
fixing-metadata is a skill published in the GitHub repository agentset-ai/agentset (2,080 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 889 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 2026-08-30.
Other skills, from other repositories
azure-openai-to-responses
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API…
ai-core/middleware
Chat lifecycle middleware hooks: onConfig, onStart, onChunk, onBeforeToolCall, onAfterToolCall, onUsage, onFinish, onAbort, onError. Use for analytics, event firing, tool caching (toolCacheMiddleware), logging, and tracing. Middleware array in chat() config, left-to-right execution order. NOT onEnd/onFinish callbacks…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
docs
Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write docs without showing the discovered readers to the user, without asking for tone, or without…
pr-sweep
Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and…
ai-core
Entry point for TanStack AI skills. Routes to chat-experience, tool-calling, media-generation, structured-outputs, adapter-configuration, ag-ui-protocol, middleware, locks, custom-backend-integration, and debug-logging, plus the skills shipped by companion packages (@tanstack/ai-persistence, @tanstack/ai-code-mode).…