A codebase search tool that finds where a feature, symbol, or idea is implemented and returns ranked file-and-line locations. It can also identify the files related to a task or ticket.

Use it to locate feature implementations, symbols, concepts, task-related files, and the surrounding code needed for a change.

It narrows a broad search to the code that is most likely relevant, rather than making you rely on one exact text match.

glia-find — 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-find

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-find/github.svg)](https://agentmods.dev/skills/james-chahwan/repo-graph/glia-find)

Your own site

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

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 947 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	$0.00065	$0.00947
Opus 5.5	$0.00026	$0.00379
Sonnet 5.5	$0.00013	$0.00189
Haiku 4.5	$0.00006	$0.00095

Measured 5d ago against content hash 3310a3354a24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glia-find 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-find/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find where something lives

Get the relevant set, ranked and located, instead of grepping for one lucky file.

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
Nodes matching a name or keyword	`find query=<text>`	`glia find . <text> --json`	`uvx mcp-repo-graph find "<text>"`
The files a task, ticket or PR title is about	`find query=<text>`	`glia find . "<text>" --files --json`	`uvx mcp-repo-graph find "<text>"`
The cluster around a concept, within a budget	`find query=<text> expand=true`	`glia pack . "<task>" --budget 4000 --json`	`uvx mcp-repo-graph find "<text>" --expand`
Their source, several at once	`read node=<a>,<b>,<c>`	open the `file:line` each row gives	`uvx mcp-repo-graph read "<a>,<b>,<c>"`

Steps

find a name or a word from the feature: checkout, UserService, /api/orders (glia find . UserService --json). Rows come back ranked, each with its kind, qname, file and line. live: false (⊘ in tables) marks a node no entry point reaches, which is likely dead code. --top-k <n> changes how many rows you get (default 20).
For a task rather than a name, ask for its files: glia find . "add a discount to checkout" --files --json ranks the files the ids and words in the text route to (an id defined in a task list, past commit messages). It needs glia history sync . for the message part; with no input it says which one was missing.
For a concept, get its neighbourhood packed to a token budget: glia pack . "<task>" --budget 4000 --json ranks the code around the matches, so related code that doesn't share the word still shows up, each node at the detail the budget buys. Over MCP, expand=true does the same ranking.
Read the top hits, not whole files. MCP read slices each to its line span with a context: footer (cross-stack callers, covering tests); with the CLI, open the file:line a row gives. glia has no read verb. Use the qname from the row when a short name is ambiguous.

Read the full file on GitHub · 31 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 · 31 lines · 65 tokens per session scan A 3310a3354a24

Subscribe to this mod's changes

glia-find is a skill published in the GitHub repository James-Chahwan/repo-graph (55 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 947 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.

Productivity

glia-find next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
glia-findJames-Chahwan/repo-graph	Skill	55	3d ago	MIT	A	65	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex