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/buildgit 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 | $0.00015 | $0.00328 |
| Opus 5 | $0.00008 | $0.00164 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Build the graph for the current project.
Both scripts live with the plugin and write into the project. Run them from the project root:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/build-graph.py" \
.claude/graph/config.json \
.claude/graph/graph-data.json \
--project-root "$PWD"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scan-project-usage.py" \
.claude/graph/graph-data.json \
--config .claude/graph/config.json \
--project-root "$PWD"
The first catalogues every agent and skill in the configured sources and computes the real cross-references between them. The second walks the scan roots and records which projects have each one actually installed on disk. The second is optional — skip it if scanRoots is empty.
Both print their counts to stderr. Report those counts to the user, and say plainly if a source root or scan root was skipped because it does not exist — a graph built from three of four configured sources is not a complete graph, and the user should hear that rather than read a success message.
If config.json does not exist, stop and tell the user to run /skill-graph:setup first.
After a successful build the MCP tools (best_skills, find_skills, get_node, and the rest) read the new data on their next call. No restart is needed.
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 · 29 lines · 15 tokens per session scan A 893400fb74fc
build is a command published in the GitHub repository QuantumWars/project-graphx (1 stars, last pushed 13d ago), licensed MIT. It adds 15 tokens to every session and 328 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.