orbit

orbit is a skill for Claude Code, Codex from JustineDevs/premortem. It costs 97 tokens per session (2,553 once invoked), scanned A, original, Apache-2.0.

A guide to Orbit, GitLab's knowledge graph for exploring code, projects, people, and their relationships. It uses glab commands to answer questions about code structure, dependencies, merge requests, and contributors.

In plain words
What is it for?
Finding where symbols are defined or called, investigating dependencies and change impact, and querying merge requests or contributor information.
Why use it?
It helps you trace how code is connected and estimate the impact of changes across projects without manually searching many files and records.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions OpenCode.

Good fit Finding where symbols are defined or called, investigating dependencies and change impact, and querying merge requests or contributor information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justinedevs/premortem/orbit
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.

Any agent
npx skills add JustineDevs/premortem --skill orbit
Clone the repo
git clone --depth 1 https://github.com/JustineDevs/premortem

Made for: Claude Code, 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 orbit

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinedevs/premortem/orbit/github.svg)](https://agentmods.dev/skills/justinedevs/premortem/orbit)
Your own site
<a href="https://agentmods.dev/skills/justinedevs/premortem/orbit"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/orbit/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 orbit

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinedevs/premortem/orbit"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/orbit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,553 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.
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 $0.00097 $0.02553
Opus 5 $0.00048 $0.01277
Sonnet 5 $0.00019 $0.00511
Haiku 4.5 $0.00010 $0.00255

Measured 9d ago against content hash 8ce84497df7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

orbit 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 9d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/local_repo_map.py, scripts/remote_repo_map.py, scripts/test_remote_repo_map.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/gitlab/orbit/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orbit (GitLab Knowledge Graph) skill

Query the GitLab Knowledge Graph (product name Orbit) via the typed glab orbit remote CLI subcommands (shipped in glab v1.94.0+). The typed CLI handles the Content-Type header, response framing, and exit codes for you — always go through glab orbit remote.

Discovery

glab orbit remote --help and glab orbit remote query --help are the authoritative usage references. For entity properties, prefer the recipes in references/recipes.md over schema introspection — recipes already encode the columns and filters that are known to work.

If you do need to introspect, call schema at most once per session and pass entity names to scope the response:

glab orbit remote schema MergeRequest Project   # scoped properties
glab orbit remote dsl                           # full query DSL JSON Schema

Always fetch the DSL with glab orbit remote dsl — it is the source of truth for the query body shape.

Calling schema without arguments returns the full ontology (~28 KB) and is rarely what you want. Re-fetching schema between turns is pure latency — schemas do not change within a session. Cache the response (or just keep it in agent context) and reuse it.

Each glab orbit remote query invocation has fixed per-call overhead (process startup, auth load, HTTPS round-trip). Prefer one aggregation query over N traversal queries when the question is "how many X grouped by Y", and batch related lookups where possible.

Running a query

Write the request body to a file and pass it to glab orbit remote query. Default output is llm (compact, agent-friendly); pass --format raw to pipe into jq. Endpoints are user-scoped — do not pass -R owner/repo.

cat > /tmp/q.json <<'JSON'
{
  "query": {
    "query_type": "traversal",
    "nodes": [
      {"id": "p",  "entity": "Project",
       "filters": {"id": {"op": "eq", "value": 278964}}},
      {"id": "mr", "entity": "MergeRequest",
       "columns": ["iid", "title", "state"]}
    ],
    "relationships": [
      {"type": "IN_PROJECT", "from": "mr", "to": "p"}
    ],
    "order_by": {"node": "mr", "property": "created_at", "direction": "DESC"},
    "limit": 5
  }
}
JSON
glab orbit remote query /tmp/q.json

Read the full file on GitHub · 234 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.

  1. 9d ago First seen · 234 lines · 97 tokens per session scan A 8ce84497df7c

Subscribe to this mod's changes

orbit is a skill published in the GitHub repository JustineDevs/premortem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,553 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories