What is skills AGENTS.md?

A set of Markdown instruction files for using Qdrant, a database designed for storing and searching vector data. It explains the project layout, available skills, and local conventions.

Use it when an agent needs to find, understand, or follow skills for Qdrant scaling, search quality, monitoring, deployment, clients, or related tasks.

It gives coding agents current, project-specific guidance instead of making them guess how the Qdrant skills repository is organized.

skills AGENTS.md — Instructions file by qdrant

Install

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.

agentmods

npx agentmods add instructions/qdrant/skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/qdrant/skills

Made for: Codex, OpenCode.

Per session 662 This file is loaded in full into every session.

When invoked 662 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00662	$0.00662
Opus 5	$0.00331	$0.00331
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 2d ago against content hash 592ee974fa35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills AGENTS.md 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 2d 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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qdrant Skills

Project overview

Agent skills for Qdrant vector search, built on the Agent Skills standard.

Repository: github.com/qdrant/skills
Format: Markdown SKILL.md files with YAML frontmatter
Compatible agents: Claude Code, Cursor, OpenCode, OpenAI Codex, Pi

Project structure

skills/
  qdrant-scaling/              # hub: links to sub-skills
    SKILL.md
    minimize-latency/          # leaf: actual guidance
      SKILL.md
    scaling-data-volume/       # hub: links to sub-skills
      SKILL.md
      horizontal-scaling/
      vertical-scaling/
      sliding-time-window/
      tenant-scaling/
    scaling-qps/
    scaling-query-volume/
  qdrant-performance-optimization/
    SKILL.md
    indexing-performance-optimization/
    memory-usage-optimization/
    search-speed-optimization/
  qdrant-search-quality/
    SKILL.md
    diagnosis/
    search-strategies/
      hybrid-search/
        search-types/
        combining-searches/
      relevance-feedback/
  qdrant-monitoring/
    SKILL.md
    debugging/
    setup/
  qdrant-clients-sdk/
  qdrant-deployment-options/
  qdrant-edge/
  qdrant-model-migration/
  qdrant-multitenancy/
  qdrant-sizing/
  qdrant-version-upgrade/

Navigating skills locally

The same tree as the published site, reached by relative path instead of URL. Each SKILL.md links to its sub-skills, and those links are the navigation mechanism; follow them rather than assembling paths yourself.

Read the SKILL.md for the relevant skill, then follow its relative links to go deeper. Skills nest up to four levels.
If you do not have a link to the skill you need, do not guess the path. Glob skills/**/SKILL.md and grep the frontmatter description fields, which carry the Use when trigger phrases.
When a tool summarizes a SKILL.md, preserve its Markdown links exactly as written. They are the only way to reach the deeper skills.

Read the full file on GitHub · 76 lines

Changes

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.

2d ago First seen · 76 lines · 662 tokens per session scan A 592ee974fa35

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository qdrant/skills (228 stars, last pushed 5d ago), licensed Apache-2.0. It adds 662 tokens to every session, about $0.0033 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.

Databases agent-skills ai-agents claude-code codex cursor embeddings

skills AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Qdrant Skills

Project overview

Project structure

Navigating skills locally

What this file has done since we first saw it

Other instructions, from other repositories

vestige CLAUDE.md

Norn CLAUDE.md

mindkeg-mcp CLAUDE.md

mindkeg-mcp AGENTS.md

amem copilot-instructions.md

neuromcp CLAUDE.md