A skill that builds and queries a structural map of a code repository in a file called graph.json. The map records files and relationships such as Markdown links and code imports.

Use it before repository work that needs structural orientation, and refresh it after file changes, added or removed files, or moves.

It gives the agent an overview of a repository without repeatedly reading every file. The map can reveal when files changed and which files are connected.

graph — Skill for Claude Code and Codex by xentivo: A skill that builds and queries a structural map…

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/xentivo/claude-plugins/graph

Any agent

npx skills add xentivo/claude-plugins --skill graph

Clone the repo

git clone --depth 1 https://github.com/xentivo/claude-plugins

Made for: Claude Code, Codex.

Or install claude-memory, the plugin that ships this one along with the rest of its 3 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/xentivo/claude-plugins/graph.svg)](https://agentmods.dev/skills/xentivo/claude-plugins/graph)

Your own site

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

Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 802 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	$0.00176	$0.00802
Opus 5	$0.00088	$0.00401
Sonnet 5	$0.00035	$0.00160
Haiku 4.5	$0.00018	$0.00080

Measured 3d ago against content hash 2161ac765aa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (generate_graph.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/claude-memory/skills/graph/SKILL.md · 55 lines

What it actually says

Strukturalna mapa repo (graph.json)

Zamiast re-czytać dziesiątki plików, najpierw skonsultuj graph.json w korzeniu projektu. Generator jest wbudowany w ten Skill — żadnych zewnętrznych narzędzi (tylko biblioteka standardowa Pythona). Kod nigdy nie opuszcza maszyny. Skill jest przenośny: dystrybuowany jako plugin claude-memory, ta sama logika działa w każdym projekcie.

Odświeżenie mapy

Uruchom wbudowany generator z korzenia projektu. ${CLAUDE_SKILL_DIR} wskazuje katalog tego Skilla niezależnie od miejsca instalacji (plugin, projekt, globalnie) i bieżącego katalogu roboczego:

python3 "${CLAUDE_SKILL_DIR}/generate_graph.py"

Zapisuje graph.json w bieżącym katalogu (deterministycznie, posortowane — czyste diffy). Odśwież zawsze, gdy:

pliki zmieniły się od pola generated w graph.json,
dodano/usunięto/przeniesiono pliki,
zaczynasz nowe zadanie wymagające orientacji w strukturze.

Sprawdzenie aktualności: porównaj graph.json generated z git log -1 --format=%cI — jeśli graf starszy niż ostatni commit lub są niezacommitowane zmiany, wygeneruj ponownie.

Odpytywanie zamiast czytania

graph.json ma kształt:

stats — liczba węzłów/krawędzi/plików,
nodes[] — {id, type, size, symbols?} (symbols = funkcje/klasy najwyższego poziomu w plikach .py),
edges[] — {from, to, kind}, kind ∈ link | wikilink | import.

Najpierw odczytaj/przefiltruj graph.json (Read albo grep), żeby ustalić: które pliki są kluczowe, co z czym powiązane, gdzie żyje dany symbol — i dopiero wtedy otwieraj konkretne pliki. To tnie zużycie tokenów względem ślepego czytania repo.

Integracja z pamięcią

Przy /save (Skill save) odśwież graph.json, żeby mapa nie odstawała od stanu repo. Opcjonalny git hook pre-commit może wołać generator automatycznie — instaluj tylko na wyraźną prośbę użytkownika.

Files

What ships with it

1 file 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.

generate_graph.py 7.6 KB runs code

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.

3d ago First seen · 55 lines · 0 tokens per session scan A 2161ac765aa1

Subscribe to this mod's changes

graph is a skill published in the GitHub repository xentivo/claude-plugins (3 stars, last pushed 7d ago), licensed MIT. It adds 176 tokens to every session and 802 once invoked, about $0.0009 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.

Code review Planning

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