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 instructions/24601/surreal-skills/agents-mdgit clone --depth 1 https://github.com/24601/surreal-skillsWrote 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/instructions/24601/surreal-skills/agents-md)<a href="https://agentmods.dev/instructions/24601/surreal-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/24601/surreal-skills/agents-md.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 | $0.07386 | $0.07386 |
| Opus 5 | $0.03693 | $0.03693 |
| Sonnet 5 | $0.01477 | $0.01477 |
| Haiku 4.5 | $0.00739 | $0.00739 |
Grade A, and why
surreal-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 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.
How it starts
The opening of the file, as written. The whole thing — 582 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Briefing: surrealdb
Structured reference for AI agents. Minimal prose, maximum signal.
Quick Start
# Check if configured
uv run {baseDir}/scripts/onboard.py --check
# Get full capabilities manifest (JSON)
uv run {baseDir}/scripts/onboard.py --agent
Capabilities
| Command | Script | What It Does | When to Use |
|---|---|---|---|
doctor |
scripts/doctor.py |
Health check: CLI, connectivity, version, storage | First run, troubleshooting, verifying environment |
doctor --check |
scripts/doctor.py |
Quick pass/fail (exit code only) | CI pipelines, pre-flight checks |
schema introspect |
scripts/schema.py |
Full schema dump (tables, fields, indexes, events) | Understanding existing database structure |
schema tables |
scripts/schema.py |
List tables with field counts and indexes | Quick overview of database contents |
schema table <name> |
scripts/schema.py |
Inspect a single table in detail | Debugging a specific table definition |
schema export |
scripts/schema.py |
Export schema as SurrealQL or JSON | Reproducible deployments, version control |
onboard --agent |
scripts/onboard.py |
JSON capabilities manifest | Agent self-discovery, integration setup |
onboard --check |
scripts/onboard.py |
Verify prerequisites | First run, CI |
Decision Trees
"User wants to create a SurrealDB project"
1. Run doctor to verify environment:
uv run {baseDir}/scripts/doctor.py
2. Is surreal CLI installed?
NO -> brew install surrealdb/tap/surreal (or see https://surrealdb.com/install)
YES -> Continue
3. Choose storage engine (LOCAL DEV -- use scoped credentials in production):
Development -> surreal start memory --user root --pass root
Single-node -> surreal start rocksdb://data/mydb.db --user root --pass root
Time-travel -> surreal start surrealkv://data/mydb --user root --pass root
Distributed -> surreal start tikv://... --user root --pass root
4. Design schema:
-> Reference rules/data-modeling.md for table/field patterns
-> Reference rules/graph-queries.md if domain has relationships
-> Reference rules/vector-search.md if semantic search needed
5. Apply schema (local dev credentials -- use scoped users in production):
surreal import --endpoint $SURREAL_ENDPOINT --user root --pass root \
--ns <ns> --db <db> schema.surql
6. Verify:
uv run {baseDir}/scripts/schema.py introspect
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 · 582 lines · 7,386 tokens per session scan A 01596ee913c5
surreal-skills AGENTS.md is an instructions file published in the GitHub repository 24601/surreal-skills (34 stars, last pushed 2mo ago), licensed MIT. It adds 7,386 tokens to every session, about $0.0369 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 instructions, from other repositories
ui-ux-pro-max-skill CLAUDE.md
Claude Code instructions for nextlevelbuilder/ui-ux-pro-max-skill, covering claude.md, project overview, search command, architecture and sync rules.
GodotPrompter CLAUDE.md
Claude Code instructions for jame581/GodotPrompter, covering godotprompter — contributor guidelines, project overview, supported platforms, conventions and skill authoring.
GodotPrompter AGENTS.md
AGENTS.md instructions for jame581/GodotPrompter, a project described as: Agentic skills framework for Godot 4.x. Domain-specific skills for AI coding agents (Claude Code, Copilot, Antigravity, Cursor).
GodotPrompter GEMINI.md
Gemini CLI instructions for jame581/GodotPrompter, a project described as: Agentic skills framework for Godot 4.x. Domain-specific skills for AI coding agents (Claude Code, Copilot, Antigravity, Cursor).
llm-ide-rules python-app.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.
research-skills CLAUDE.md
Claude Code instructions for neuromechanist/research-skills, a project described as: A skill marketplace for academic research: from project management to literature review, making figures and writing reports and grants.