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 commands/quantumwars/project-graphx/viewgit clone --depth 1 https://github.com/QuantumWars/project-graphxWhat 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 | $0.00022 | $0.00551 |
| Opus 5 | $0.00011 | $0.00275 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
view scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open the graph viewer in the user's browser, pointed at the current project.
This is the default viewer. It needs nothing beyond node, which the plugin already
requires — unlike /skill-graph:app, which costs a one-time ~280 MB Electron download.
Prefer this command unless the user specifically asks for the desktop app.
Preconditions
.claude/graph/graph-data.json must exist. If it does not, stop and tell the user to run
/skill-graph:build. Do not start the server to "show them the empty state" — it exits
with that same instruction, so starting it only adds a step.
Launch
Run it in the background and report the URL it prints:
cd "$(pwd)" && node "${CLAUDE_PLUGIN_ROOT}/server/viewer-server.js" \
--data-dir "$(pwd)/.claude/graph" &
--data-dir is what makes it show this project. Pass it as an absolute path built from
pwd at the moment the command runs — do not write a placeholder like $PROJECT_DIR and
expect the shell to fill it in.
The server prints the URL it bound to, the data directory it is showing, and how to stop it. Report the URL to the user; it opens their browser automatically. If the default port is taken it walks upward until it finds a free one, so read the printed URL rather than assuming a port number.
Options
--port N— pin a port instead of letting it choose. If that exact port is busy the server exits rather than silently moving, because a pinned port usually means something else (a bookmark, a proxy) is relying on it.--no-open— start the server without launching a browser.
Stopping it
It runs until stopped. pkill -f viewer-server.js ends it. Say so if the user asks how to
close it — closing the browser tab leaves the server running.
What works here
Everything the desktop app does: notes, ratings and reveal-in-file-manager all write
through the same code the MCP server uses, so a note added in the browser is visible to
get_node and survives a rebuild. There is no read-only limitation to warn the user
about.
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 · 57 lines · 22 tokens per session scan A 318cff9a69d0
view is a command published in the GitHub repository QuantumWars/project-graphx (1 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 551 once invoked, about $0.0001 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.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.