A setup workflow for adding a workspace of Git repositories to Graphify, a tool that builds a graph of code relationships.

Use it to configure Graphify across one or more repositories and keep its code graph updated after repository operations.

It guides installation, configuration, graph building, and repository hook setup while asking for consent before changes are made.

graph-setup — Skill for Claude Code by choiyounggi/dev-loop

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add choiyounggi/dev-loop

Claude Code

/plugin install dev-loop

Made for: Claude Code.

Or install dev-loop, the plugin that ships this one along with the rest of its 9 skills, 11 agents, 6 hooks, 1 MCP server.

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/choiyounggi/dev-loop/graph-setup/github.svg)](https://agentmods.dev/skills/choiyounggi/dev-loop/graph-setup)

Your own site

<a href="https://agentmods.dev/skills/choiyounggi/dev-loop/graph-setup"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/graph-setup/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/choiyounggi/dev-loop/graph-setup"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/graph-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,247 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	$0.00106	$0.01247
Opus 5.5	$0.00042	$0.00499
Sonnet 5.5	$0.00021	$0.00249
Haiku 4.5	$0.00011	$0.00125

Measured 1mo ago against content hash 2531317e17a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graph-setup 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 1mo 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.

skills/graph-setup/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graph-setup — onboard a workspace onto the graphify code graph

Every install and every build in this skill runs only after the user said yes to an explicit AskUserQuestion. Nothing here runs from a SessionStart hook — hooks/graph-nudge.sh only reports; this skill is the only place that builds or installs.

Steps

Step 1 — detect graphify

Run command -v graphify.

Found → continue to Step 2.
Absent → ask with AskUserQuestion:
- Option 1: "Install with pipx (Recommended)" — runs the exact command pipx install graphifyy (the PyPI package name is graphifyy, not graphify — state this to the user).
- Option 2: "Skip — stop here"
On yes, run pipx install graphifyy </dev/null > "$tmp" 2>&1 and show the tail of $tmp. On no, stop here — nothing else in this skill runs.

Step 2 — configure the workspace

Run sh ${CLAUDE_PLUGIN_ROOT}/scripts/resolve-tools.sh --role workspace.

Already has roots? Use them as-is.
Unset ({"kind":"default"})? Ask the user for the root directory path(s) and the scope, same choice as /dev-loop:configure:
- Global (all projects): ~/.claude/dev-loop/tools.json
- Per-repo (committed, team-shared): <repo>/.dev-loop/tools.json
Write the key into that file (create it as {} first if it does not exist yet):
```
jq '. + {workspace: {roots: $r, depth: 2, exclude: ["node_modules","graphify-out"]}}'
```

Step 3 — show status

Run, with the configured depth/exclude/roots:

sh ${CLAUDE_PLUGIN_ROOT}/scripts/graph-workspace.sh --status --depth <n> [--exclude <glob>]... -- <root>...

Print every returned line verbatim as a table: repo, freshness, hooks.

Step 4 — build absent graphs

Collect every repo Step 3 reported absent. If there are none, skip to Step 5. Otherwise, before asking, brief the user with this sentence verbatim:

graphify update is AST-only (no LLM) and preserves semantic nodes from an earlier full run while replacing only code nodes, so the result is not identical to a full /graphify build.

Read the full file on GitHub · 110 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.

1mo ago First seen · 110 lines · 106 tokens per session scan A 2531317e17a4

Subscribe to this mod's changes

graph-setup is a skill published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,247 once invoked, about $0.0004 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 2026-09-17.

Claude Code DevOps and cloud Git and workflow best-practices claude-code-plugin developer-tools knowledge-base llm-agents

update

Safe cc10x upgrade through the Claude Code plugin CLI. Lists every installed scope, refreshes the marketplace, updates each scope, and optionally carries local patches over to the new install. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new…

romiluz13/cc10x · 108 tokens

resolving-merge-conflicts

Use when a git merge or rebase reports conflicts and the operation is in progress.

romiluz13/cc10x · 25 tokens

kb-conflict-resolve

Guide an agent through resolving open git rebase conflicts on degraded KB concepts.

BeppeTemp/cartographer · 21 tokens

git-commit

Create well-structured git commits using the Conventional Commits specification. Use when asked to "commit changes", "create a git commit", "stage and commit", "write a commit message", or "/commit". Analyzes diffs to auto-detect type and scope, generates semantic commit messages, and supports intelligent file staging.

fabioc-aloha/Alex_Skill_Mall · 70 tokens

git-workflow

Consistent git practices, recovery patterns, and safe operations.

fabioc-aloha/Alex_Skill_Mall · 16 tokens

github-wiki-flat

GitHub Wiki has a flat namespace — no real folders, sidebar ordering tricks, link gotchas.

fabioc-aloha/Alex_Skill_Mall · 24 tokens