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.
npx agentmods add skills/a2ngerer/claude_onboarding_agent/graphify-setupnpx skills add a2ngerer/claude_onboarding_agent --skill graphify-setupgit clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agentWrote 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.
[](https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/graphify-setup)<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/graphify-setup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/graphify-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00086 | $0.02173 |
| Opus 5 | $0.00043 | $0.01086 |
| Sonnet 5 | $0.00017 | $0.00435 |
| Haiku 4.5 | $0.00009 | $0.00217 |
Grade B, and why
graphify-setup 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- G5: verify `graphify` appears in `.claude/settings.json` or `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graphify Setup — Knowledge-Graph Integration
This skill installs Graphify, registers its /graphify slash command and PreToolUse hook with Claude Code, optionally builds an initial graph for the current project, and records a short pointer block in CLAUDE.md.
It is safe to run standalone via /graphify-setup, OR it is delegated to from any host setup skill (coding-setup, knowledge-base-setup, research-setup, data-science-setup, web-development-setup) when the user opts in.
Language: Use detected_language from handoff context, or detect from the user's first message and use it throughout. All generated file content stays in English.
Existing CLAUDE.md: never silently overwritten. Graphify's pointer block lives inside an attributed delimited section (<!-- onboarding-agent:start setup=<host_setup_slug> skill=graphify-setup section=graphify -->). When this skill runs standalone, the setup= attribute is graphify. When delegated to from another host setup, the attribute matches that host — so /upgrade-setup keeps every skill's block cleanly addressable.
Step 1: Detect handoff vs standalone
If a HANDOFF_CONTEXT was passed (invoked from a host setup), read:
host_setup_slug(one ofcoding,data-science,knowledge-base,research,web-development)host_skill_slug(the host skill's directory name)run_initial_build(bool)install_git_hook(bool)
If no handoff, set:
host_setup_slug: "graphify"host_skill_slug: "graphify-setup"run_initial_build: null(ask in Step 3)install_git_hook: null(ask in Step 3)
Also detect whether CLAUDE.md already exists in the working directory → existing_claude_md: true|false.
Step 2: Explain what Graphify does (standalone only)
Skip this step if invoked via handoff — the host skill already asked.
Print ONCE (adapt to detected language):
"Graphify is a local, open-source knowledge graph for Claude Code (https://github.com/safishamsi/graphify).
What it does for you:
- Indexes your project into a graph: code symbols (25 languages via tree-sitter), Markdown, PDFs, diagrams, images, audio/video.
- Registers a PreToolUse hook that consults the graph BEFORE Claude runs Grep / Glob / Read on your repo — cuts token cost substantially on large codebases or mixed-media corpora.
- Adds a
/graphifyslash command for natural-language queries against the graph (/graphify query,/graphify path,/graphify explain).This setup installs the
graphifyyPython package (viauv tool install, orpipxas fallback), runsgraphify installto wire up the hook and slash command, optionally builds the initial graph for this project, optionally installs a git hook that refreshes the graph on commit, and records a pointer block in your CLAUDE.md.Shall I proceed? (yes / no)"
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 · 154 lines · 86 tokens per session scan B 2a1a77e6e699
graphify-setup is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,173 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…