A codebase knowledge-graph integration built around the graphify command-line tool. It maps relationships in a software project so codebase questions can be answered using that map.

Use it to keep a project map current and query relationships between files, modules, and other parts of a codebase while working on software.

It reduces the need to repeatedly search through many files to understand how code is connected. The graph is refreshed automatically and can be disabled through a user-controlled setting.

auto-graph — Skill for Claude Code and Codex by Jerry0022: A codebase knowledge-graph integration built around the graphify command-line…

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/jerry0022/dotclaude/auto-graph

Any agent

npx skills add Jerry0022/dotclaude --skill auto-graph

Clone the repo

git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code, Codex.

Or install devops, the plugin that ships this one along with the rest of its 23 skills, 12 agents, 5 hooks, 3 MCP servers.

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/jerry0022/dotclaude/auto-graph.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/auto-graph)

Your own site

<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-graph"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-graph.svg" alt="Measured on agentmods" height="20"></a>

Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,977 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00207	$0.01977
Opus 5	$0.00103	$0.00988
Sonnet 5	$0.00041	$0.00395
Haiku 4.5	$0.00021	$0.00198

Measured 4d ago against content hash ad8d3aad8503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-graph 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 4d 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.

plugins/devops/skills/auto-graph/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-graph — Codebase Knowledge Graph (default-on, opt-out)

Thin orchestration over the real graphify CLI. graphify stays the single source of truth — this skill reimplements nothing. It detects, auto-installs if missing, freshens the graph, and queries it. graphify enforcement is enabled by default in every project — no consent prompt, no offer to confirm. The graph is kept fresh automatically and broad searches are hard-gated toward it — see Enforcement.

Hard rules

No consent prompt, ever. Enforcement is default-on. Never ask the user to confirm enabling graphify and never write a consent record on their behalf — .claude/graphify.json / ~/.claude/graphify.json are read-only from hooks; only the user edits them, manually, to opt out.
Never run graphify claude install. That command writes graphify's own PreToolUse hook + CLAUDE.md skill, which collides with the devops plugin's PreToolUse hooks (the project-map re-scoping hint and pre.tokens.guard.js). Our enforcement is devops-owned instead (single, ordered hook chain).
Never install graphify's own git hooks. They pop a console window on Windows on every commit/checkout. ss.graphify actively removes them (graphify hook uninstall) if present — devops owns graph freshness instead, windowlessly, via SessionStart + PreToolUse self-heal.
Do not touch project-map. It is a different layer (cheap always-on orientation, not on-demand deep retrieval).

Step 1 — Detect graphify

Probe with the generic helper (resolves the plugin root via the cache path or this source repo):

node "${CLAUDE_PLUGIN_ROOT}/scripts/check-tool.js" graphify --version

Parse the single JSON line:

{"installed":true,...} → go to Step 3.
{"installed":false} → go to Step 2.

Step 2 — Install if missing (background, no confirmation needed)

If graphify is missing, ss.graphify already kicked off a best-effort, windowless background install (uv tool install graphifyy) at SessionStart — this is auto-installed, not offered. If you land here mid-session and the CLI still isn't on PATH, you may run the same command directly:

Read the full file on GitHub · 165 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.

4d ago First seen · 165 lines · 207 tokens per session scan A ad8d3aad8503

Subscribe to this mod's changes

auto-graph is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed today), licensed MIT. It adds 207 tokens to every session and 1,977 once invoked, about $0.0010 per session on Opus 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 2026-08-31.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens