vellis: Skill for Codex

.agents/skills/rtg-knowledge-graph-mcp/SKILL.md

rtg-knowledge-graph-mcp is a skill for Codex from volantlabs/vellis. It costs 87 tokens per session (4,724 once invoked), scanned A, original, Apache-2.0.

A guide for operating the Vellis RTG Knowledge Graph MCP server, which lets an agent validate, query, change, and migrate graph data. An MCP server provides tools that an AI agent can call.

In plain words
What is it for?
Use it to inspect graph state, discover types, validate data, run queries, stage schema or data changes, apply migrations, and replay or recover the change ledger.
Why use it?
It provides a controlled process for discovering the graph's schema, validating its state, staging changes, and recovering from problems. This reduces unsafe writes and incorrect assumptions about stored data.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

This is volantlabs/vellis's own configuration. It tells Codex how to work on vellis itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vellis configures →

Reuse

Borrowing it

Nothing to install: this file belongs to volantlabs/vellis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/volantlabs/vellis/main/.agents/skills/rtg-knowledge-graph-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/volantlabs/vellis

Made for: Codex.

Wrote 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.

agentmods badge for rtg-knowledge-graph-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/volantlabs/vellis/rtg-knowledge-graph-mcp/github.svg)](https://agentmods.dev/skills/volantlabs/vellis/rtg-knowledge-graph-mcp)
Your own site
<a href="https://agentmods.dev/skills/volantlabs/vellis/rtg-knowledge-graph-mcp"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/rtg-knowledge-graph-mcp/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.

agentmods 80×15 button for rtg-knowledge-graph-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/volantlabs/vellis/rtg-knowledge-graph-mcp"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/rtg-knowledge-graph-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.04724
Opus 5 $0.00044 $0.02362
Sonnet 5 $0.00017 $0.00945
Haiku 4.5 $0.00009 $0.00472

Measured 8d ago against content hash 463e0d4cdae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rtg-knowledge-graph-mcp 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 8d 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/skills/rtg-knowledge-graph-mcp/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTG Knowledge Graph MCP

Use the RTG MCP server as a controller-facing graph memory, not as a loose JSON store. Start by validating the connection and reading system state, discover live schema before writing, use the correct mutation lane, and query through rtg_execute_query instead of manually scanning objects.

Operator Card

  1. Validate the connection with rtg_validate_graph({}).
  2. Read rtg_get_system_state({}) to classify the app as empty, schema-only, populated, staged, or needing replay.
  3. If examples are needed, call rtg_get_usage_guide with everyday_life_schema, schema_design, capabilities, workflow_patterns, request_patterns, mcp_bootstrap_checklist, operator_card, schema_staging_minimal, tool_call_shapes, live_write, lookup_examples, query_examples, recovery_and_replay, migration_history, or migration_abandonment.
  4. Discover available anchor types with rtg_discover_anchor_types, then read details with rtg_get_schema_pack.
  5. Stage initial schema or schema evolution with rtg_stage_schema_migration unless you need the advanced normalized-batch surface.
  6. Make staged schema live with rtg_apply_migration_cutover.
  7. Resolve existing object UUIDs with rtg_resolve_anchor_by_fact or rtg_execute_query lookup examples before link writes; dry-run risky graph changes with rtg_validate_live_graph_changes or repeated anchor-with-facts records with rtg_validate_live_anchor_records.
  8. Write live graph data with rtg_apply_live_graph_changes; for repeated anchor plus required-facts ingestion, use rtg_apply_live_anchor_records.
  9. Preserve recovery evidence with persisted snapshots, snapshot load, restore, ledger replay, replay verification, and migration history.

First Calls

If the RTG MCP tools are not already connected, use the repo-generated MCP metadata before writing custom scripts. Prefer the focused mcp-config CLI output, which is the complete client block and launches the stdio server from absolute paths. The larger diagnostic metadata exposes the same block as mcp.client_config. For a Vellis app that is already running locally, use mcp.transports.localhost_http.client_config and connect to http://127.0.0.1:8765/mcp by default. The localhost HTTP transport is unauthenticated and should remain bound to 127.0.0.1.

Read the full file on GitHub · 377 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 8d ago First seen · 377 lines · 87 tokens per session scan A 463e0d4cdae8

Subscribe to this mod's changes

rtg-knowledge-graph-mcp is a skill published in the GitHub repository volantlabs/vellis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 4,724 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

omnigraph

Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…

ModernRelay/omnigraph · 94 tokens

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

binder-modeling

Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.

mpazik/Binder · 74 tokens

binder-cli

Binder CLI for knowledge graph operations — CRUD, search, schema inspection, transaction import, docs rendering. Use when asked to "query binder", "search records", "create a record", "check the schema", "import transactions", "undo changes", or work with a binder workspace.

mpazik/Binder · 60 tokens

binder-import

Import external data into a Binder workspace. Handles CSV, JSON, YAML, Markdown files, and directories of Markdown. Use when asked to "import data", "load records from a file", "ingest documents", "migrate data into binder", or bulk-create records from an external source.

mpazik/Binder · 62 tokens

claude-memory

Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…

mkupermann/throughline · 81 tokens