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/pushgit 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 | $0.00016 | $0.00909 |
| Opus 5 | $0.00008 | $0.00454 |
| Sonnet 5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
push scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Register the current repository's own .claude/ skills, agents, commands and output styles as
sources in the global catalogue, then rebuild it so they are visible from every project.
The repository keeps its files. Nothing is copied anywhere — a source is a directory the global build reads in place, so a skill edited here is the skill the catalogue reports tomorrow.
1. Check there is a global catalogue to push to
echo "${GRAPH_DATA_DIR:-<unset>}"
If it is unset there is no global catalogue and nothing to push to. Say so and stop: the fix is
/skill-graph:setup-global, not this command. Do not create one here — choosing that location,
and merging settings.json, is that command's job and it asks the user first.
2. See what is unregistered
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/unpushed.py" "$PWD"
Read the JSON. Four fields matter:
unpushed— roots the global config has never heard of. These are what this command registers.stale— roots it knows, holding a file newer than the built graph. Nothing to register; step 4 alone fixes these.registered— already known and current. Report the counts; do nothing.uncatalogued— real infrastructure that cannot become a node, today only.claude/hooks. Report it so "nothing to push" never quietly means "I skipped these".
If unpushed and stale are both empty, say so and stop. Do not rebuild for nothing.
3. Add each unpushed root to the global config
Read $GRAPH_DATA_DIR/config.json, append one entry per unpushed root, write it back. Merge —
never write the file whole. It holds every other repo's registration, and replacing it silently
un-registers all of them.
Each entry takes the kind and root straight from the JSON, and repo is this repository's
directory name:
{ "repo": "<dirname of $PWD>", "root": "<absolute root from unpushed>", "kind": "<kind>" }
The root must be absolute. A relative root resolves against whichever project the build runs from, so in a shared catalogue it points somewhere different every time.
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 · 90 lines · 16 tokens per session scan A b5a0aeeb702f
push is a command published in the GitHub repository QuantumWars/project-graphx (1 stars, last pushed 13d ago), licensed MIT. It adds 16 tokens to every session and 909 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.