A codebase map that shows services, entry points, and how requests move between parts of a repository. It also reports areas the map cannot connect confidently.

Use it to understand a repository's architecture, trace its main flows, and check whether the map is missing important connections.

It gives you the repository's overall shape before you open files one by one, which reduces guesswork in a large or unfamiliar codebase.

glia-orient — Skill for Claude Code by James-Chahwan/repo-graph

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 James-Chahwan/repo-graph --skill glia-orient

Clone the repo

git clone --depth 1 https://github.com/James-Chahwan/repo-graph

Made for: Claude Code.

Or install repo-graph, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-orient/github.svg)](https://agentmods.dev/skills/james-chahwan/repo-graph/glia-orient)

Your own site

<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia-orient"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-orient/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/james-chahwan/repo-graph/glia-orient"><img src="https://agentmods.dev/badge/skills/james-chahwan/repo-graph/glia-orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,044 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.01044
Opus 5.5	$0.00027	$0.00418
Sonnet 5.5	$0.00013	$0.00209
Haiku 4.5	$0.00007	$0.00104

Measured 5d ago against content hash 5e7026d36c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glia-orient 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 5d 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.

claude-plugin/skills/glia-orient/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orient in a codebase

Get the shape of a repo from its structural graph instead of opening files one by one.

Transports

Use whichever is available, in this order: the repo-graph MCP tools when loaded (mcp__repo-graph__<tool>, or mcp__plugin_repo-graph_repo-graph__<tool> from the Claude Code plugin; they may be deferred, so search your tool list first); the glia CLI when on PATH; else uvx --from glia-cli glia <command> .. (no install; the first run downloads the wheel); else uvx mcp-repo-graph <verb>. The MCP tools and uvx mcp-repo-graph print the same text; the glia CLI answers the same question with --json rows (file, line, tier). Run any of them at the repo root (. below).

Want	MCP tool call	glia CLI	uvx mcp-repo-graph
Can the graph be trusted here?		`glia health . --json`
Overview	`orient`	`glia arch . --json` and `glia flows . --json`	`uvx mcp-repo-graph orient`
Map around one node	`orient seed=<node>`	`glia trace . <node> --json`	`uvx mcp-repo-graph orient "<node>"`
Whole-repo map	`orient full=true`	`glia arch . --include-shared --json`	`uvx mcp-repo-graph orient --full`
Where the graph is blind	the overview's Blind spots	`glia coverage . --json`	`uvx mcp-repo-graph orient`
What could not be paired, what looks dead		`glia gaps . --json`

The glia CLI has no orient verb: health, arch, flows, coverage and gaps answer its parts.

Steps

On a repo you have not seen before, run glia health . --json first (CLI only). Its verdict is the worst row: per boundary mechanism (http, grpc, rpc, graphql, queue, ws) how much of the client and server side the graph pairs (OK, DEGRADED, BLIND, with the reason and the measure, e.g. servers reached 1% of 436), then parse (code files no parser read), workspace_unresolved (in-repo packages imported by name and bound to nothing) and the dead-symbol share. A BLIND mechanism means every answer through it (a contract break, an unpaired route, a cross-service trace) is glia not seeing, not an absence: say so in the report and grep that part. A library role is never judged on reach.
Run the overview. Over MCP it lists node and edge counts, the node kinds, the entry points (routes, CLI commands, handlers, jobs) and a Blind spots section. On the CLI, glia arch . --json gives the services and the links between them (HTTP, gRPC, queue, event), and glia flows . --json the entry points with where each one goes.
Read the blind spots before trusting any "not found": glia coverage . --json lists the edge kinds and languages this repo's graph under-links, how many it did find, and what to grep instead. Those are the places grep is still needed.
glia gaps . --json lists what could not be paired (a client call with no server route, a route nothing calls) and the likely-dead symbols.
To zoom in on one area, take a node name from the overview or from a find and seed the map with it (orient seed=<node>, or glia trace . <node> --json for the flows through it).

Read the full file on GitHub · 36 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.

5d ago First seen · 36 lines · 67 tokens per session scan A 5e7026d36c3d

Subscribe to this mod's changes

glia-orient is a skill published in the GitHub repository James-Chahwan/repo-graph (55 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,044 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-02.

Planning

glia-orient next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
glia-orientJames-Chahwan/repo-graph	Skill	55	3d ago	MIT	A	67	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code