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/appgit 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 | $0.00017 | $0.00521 |
| Opus 5 | $0.00009 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
app scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Open the desktop viewer, pointed at the current project's graph.
Check first whether the user actually wants this one. /skill-graph:view shows the
same graph in a browser with the same features and no download. This command is worth its
cost only if they specifically want a native window. If they have not said so, offer
/skill-graph:view instead.
Preconditions
.claude/graph/graph-data.json must exist. If it does not, stop and tell the user to run /skill-graph:build. The app opens without it, but shows only setup instructions.
First run — install the viewer's dependencies
The viewer is Electron and its dependencies are not bundled with the plugin; they are large and platform-specific. Check first:
test -d "${CLAUDE_PLUGIN_ROOT}/app/node_modules" && echo present || echo missing
If missing, tell the user this is a one-time ~280 MB install and ask before running it:
cd "${CLAUDE_PLUGIN_ROOT}/app" && npm install
Launch
GRAPH_DATA_DIR="$PWD/.claude/graph" \
npx --prefix "${CLAUDE_PLUGIN_ROOT}/app" electron "${CLAUDE_PLUGIN_ROOT}/app" &
GRAPH_DATA_DIR is what makes the app show this project. Run the block as written — it
reads $PWD before anything changes directory, so the path is the real project. Do not
rewrite it into a cd followed by a placeholder like $PROJECT_DIR; an unset variable
expands to nothing, GRAPH_DATA_DIR becomes /.claude/graph, and the app then refuses to
start rather than writing a rating somewhere nobody reads.
Packaging (--pack)
Only when the user passes --pack. Builds a standalone .app:
cd "${CLAUDE_PLUGIN_ROOT}/app" && npm run pack
State plainly that the pack script targets macOS arm64 only — it is not a cross-platform build, and on any other platform the user should run the app with npm start instead. The packaged app still needs GRAPH_DATA_DIR set, or a --data-dir <path> argument, to find a project.
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 · 54 lines · 17 tokens per session scan A 6fbdf079d853
app is a command published in the GitHub repository QuantumWars/project-graphx (1 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 521 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.