A coding skill that turns code, documents, papers, images, or videos into a lasting knowledge graph, a network showing how information is connected. It can also answer questions about a codebase and its structure.

Use it to explore a codebase, inspect architecture, trace file relationships, and query previously extracted project knowledge.

It gives an agent a way to understand relationships across files and project content instead of searching each item in isolation.

graphify — Skill by dsswift

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.

agentmods

npx agentmods add skills/dsswift/ion/graphify

Any agent

npx skills add dsswift/ion --skill graphify

Clone the repo

git clone --depth 1 https://github.com/dsswift/ion

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,518 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin 89% copy Near-identical to another mod 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	$0.00076	$0.10518
Opus 5	$0.00038	$0.05259
Sonnet 5	$0.00015	$0.02104
Haiku 4.5	$0.00008	$0.01052

Measured yesterday against content hash c63e65df8f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

graphify scanned grade B with 1 finding 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 yesterday.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the p

Origin

This is a copy

89% identical to graphify — 74 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.ion/skills/graphify/SKILL.md · 730 lines

How it starts

The opening of the file, as written. The whole thing — 730 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/graphify

Ion note — read this before any step below.

Query the existing graph. Do not probe for it, do not rebuild it, and do not install anything.
graphify query "<identifier or question>"
That is the whole procedure for a codebase question in this repo. Run it as your first action. If it fails — graphify absent, no graph in this clone — the failure costs ~2ms and is your signal to answer with Grep/Glob/Read instead. Fall through silently; a missing graph is not a setup error.

Do not run Step 1 below. It offers to install graphify when missing. Installing a tool into a contributor's environment because a repo skill mentions it is not a decision this skill gets to make. Ion treats graphify as optional for contributors: nothing in the project requires it, and a clone without it is fully supported.

Do not run a full extraction unasked. If the operator wants a graph built, make bootstrap (or make graph-ensure) is theirs to run. Ion builds with --code-only and clusters with --no-label, so the pipeline stays offline and needs no API key — anything below implying a semantic/LLM pass does not apply to routine Ion use.

Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.

Usage

/graphify                                             # full pipeline on current directory (HTML viz; add --obsidian for a vault)
/graphify <path>                                      # full pipeline on specific path
/graphify https://github.com/<owner>/<repo>           # clone repo then run full pipeline on it
/graphify https://github.com/<owner>/<repo> --branch <branch>  # clone a specific branch
/graphify <url1> <url2> ...                           # clone multiple repos, build each, merge into one cross-repo graph
/graphify <path> --mode deep                          # thorough extraction, richer INFERRED edges
/graphify <path> --update                             # incremental - re-extract only new/changed files
/graphify <path> --directed                            # build directed graph (preserves edge direction: source→target)
/graphify <path> --whisper-model medium                # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only                       # rerun clustering on existing graph
/graphify <path> --no-viz                             # skip visualization, just report + JSON
/graphify <path> --html                               # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg                                # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml                            # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j                              # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687   # push directly to Neo4j
/graphify <path> --falkordb                           # generate graphify-out/cypher.txt for FalkorDB
/graphify <path> --falkordb-push falkordb://localhost:6379   # push directly to FalkorDB
/graphify <path> --mcp                                # start MCP stdio server for agent access
/graphify <path> --watch                              # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify <path> --wiki                               # build agent-crawlable wiki (index.md + one article per community)
/graphify <path> --obsidian --obsidian-dir ~/vaults/my-project  # write vault to custom path (e.g. existing vault)
/graphify add <url>                                   # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name"                   # tag who wrote it
/graphify add <url> --contributor "Name"              # tag who added it to the corpus
/graphify query "<question>"                          # BFS traversal - broad context
/graphify query "<question>" --dfs                    # DFS - trace a specific path
/graphify query "<question>" --budget 1500            # cap answer at N tokens
/graphify path "AuthModule" "Database"                # shortest path between two concepts
/graphify explain "SwinTransformer"                   # plain-language explanation of a node

Read the full file on GitHub · 730 lines

Files

What ships with it

8 files 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.

yesterday First seen · 730 lines · 76 tokens per session scan B c63e65df8f11

Subscribe to this mod's changes

graphify is a skill published in the GitHub repository dsswift/ion (4 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 10,518 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 89% identical to graphify, differing in 74 lines, and is treated as a copy.

Data and AI Research Writing and docs agent-framework agent-runtime ai-agent anthropic cli golang

optimizer

Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.

inclusionAI/AWorld · 18 tokens

text2agent

Creates new agents from user requirements by generating Python implementation and mcpconfig.

inclusionAI/AWorld · 19 tokens

tiktok_download

Single-file TikTok/Douyin video download and traffic metrics via TikHub API using only httpx; optional persisted raw API JSON plus a stdlib post-processor emitting CSV and simplified JSON. Supports one URL or concurrent batch (max 10 workers). No dependency on any project codebase.

inclusionAI/AWorld · 63 tokens

app_evaluator

A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).

inclusionAI/AWorld · 33 tokens

self_evolve

Use for framework-gated self-evolve workflows in AWorld: evolve skills, create trajectory-backed proposals, inspect self-evolve run artifacts, run aworld-cli optimize, or prepare verified apply decisions through aworld.selfevolve gates.

inclusionAI/AWorld · 51 tokens

video-subtitles-and-audio-insert-workflow

Burn hard subtitles from UTF-8 SRT files using moviepy 2.x with CJK-capable system fonts; tune font size, placement, stroke, and encode settings (bitrate or CRF) to avoid oversized outputs. Documents ffprobe/ffmpeg workflows for inspection, encoding, and batch jobs; troubleshooting for fonts, bitrate, and pacing.…

inclusionAI/AWorld · 140 tokens

graphify