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 skills/quantumwars/project-graphx/using-the-graphnpx skills add QuantumWars/project-graphx --skill using-the-graphgit 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 | $0.00062 | $0.00899 |
| Opus 5 | $0.00031 | $0.00449 |
| Sonnet 5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
using-the-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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the skill graph
The skill-graph MCP server answers questions about the agents and skills catalogued for this
project from data built by scanning real files. Prefer it to reading directories: a .claude/skills
listing gives you names, and the graph gives you what each one is, what references it, and who
already uses it.
First, is there a graph?
Every tool fails with the same message when the project has no graph yet: No graph found at
<path>. That is a first-run state, not a fault. Tell the user to run /skill-graph:setup and then
/skill-graph:build. Do not fall back to guessing from filenames without saying that is what you
are doing.
Which tool answers which question
| The question | The tool |
|---|---|
| "what should I install for X" | search_ranked, then get_file_set to narrow |
| "what is this skill" | get_node |
| "what is important here" | best_skills |
| "what else relates to this" | graph_neighbors, related_by_connections |
| "how are these two connected" | graph_path |
| "who already uses this" | projects_using |
| "what does this project have" | project_installed_skills |
| "what categories/tags exist" | list_categories, list_tags |
find_skills is a fuzzy name/description match; search_ranked also weighs how connected and how
used each hit is. Reach for search_ranked when the user described a need, and find_skills when
they named a thing.
What the numbers mean, and do not mean
An edge exists because one file's text mentions another node's name — a real, counted occurrence, not a curated relationship. High degree means "widely mentioned", which is usually but not always "important": a skill named after a common word accumulates edges by coincidence. Say "referenced by N others" rather than "the most important", because the first is what was measured.
usedBy and usesCount come from a filesystem scan of the configured scan roots. Absent means "not
found under those roots" — never "unused". If scanRoots is empty, every one of these numbers is
zero and reporting them as usage would be wrong.
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 · 71 lines · 62 tokens per session scan A 3cdac2add9fa
using-the-graph is a skill published in the GitHub repository QuantumWars/project-graphx (1 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 899 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.