Borrowing it
Nothing to install: this file belongs to alfadur7/llm-wiki-newsroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfadur7/llm-wiki-newsroom/main/.claude/commands/wiki-graph.mdgit clone --depth 1 https://github.com/alfadur7/llm-wiki-newsroomWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-graph)<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-graph"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-graph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-graph"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00807 |
| Opus 5 | $0.00000 | $0.00404 |
| Sonnet 5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
wiki-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 12d ago.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the LLM Wiki knowledge graph.
Usage: /wiki-graph
Traversal Pattern
Outside the matrix — Meta layer (deterministic). The Editor-in-Chief calls tools/build.py and reports the result.
| Cycle | Owner |
|---|---|
| Trigger | Editor-in-Chief |
| Build | tools/build.py (deterministic — 5 phases: graph → clusters → contradictions → index → dependencies) |
| Verify | Copy Editor (tools/lint.py graph clusters recommended) |
| Log | Editor-in-Chief (log.md append) |
Operation
python tools/build.py graph— rebuild the graph only (graph/_graph.jsononly —graph.htmlis a committed static shell, see item 3). Does not trigger downstream phases.- A full rebuild is
python tools/build.py(auto-invoked by ingest and by lint --fix). graph/graph.htmlis a single committed Sigma.js v3 static shell — it loads_graph.json·_clusters.json(at init) +_pages.json(lazily on click) directly viafetch(). A rebuild only regenerates those JSON files (no separate JS wrapper or inline).- After the build,
python tools/lint.py graph clustersis recommended — checks for isolated hubs and unnamed groups.
graph.html is not just a visualization but also includes a reading panel — clicking a node renders that page's Markdown body in the right-hand panel (marked), and you can move between node and body by clicking the in-body [[wikilinks]], backlinks, and connection list, so it is browsable without Obsidian. The body, link resolution, and backlinks are held in _pages.json (generated by the clusters phase's pages.run from wiki/*.md·_build_id_map·wiki/_backlinks.json) and fetched on click. Because it is fetch-based it must be opened via a web server (a file:// double-click is unsupported — locally, python -m http.server). On mobile, a responsive layout (viewport meta + @media queries) renders the navigation as a sidebar drawer and the reading panel as a bottom sheet.
Deep link: open a specific node via the URL hash — #node=<wiki-path> (exact) or #q=<slug/text> (idmap resolution → search on failure). Used together with a hosting deployment, a RAG answer's <base>/<slug>#q=<source-slug> link connects to the primary source in one tap. Phone hosting deployment is /wiki-export + operations/graph-hosting-setup.md.
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.
- 12d ago First seen · 44 lines · 0 tokens per session scan A 10a693e31153
wiki-graph is a command published in the GitHub repository alfadur7/llm-wiki-newsroom (85 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 807 tokens. 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 2026-08-30.
Other commands, from other repositories
slm-loop
Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim.
review
When reviewing the code changes, the agent should apply general best practices to ensure high code quality. Key areas of evaluation include.
mt-onboard
Shortcut to the canonical Memtrace codebase exploration skill.
add-source
Guided add of a new source store to sources/supported-stores.json — evaluate, register, refresh, verify catalog impact.
choose-model
Compare current models across configured AI providers and produce an executable plan without running paid work. Use when the user asks which model or provider should perform a task.
checklist
Generate a custom checklist for the current feature based on user requirements.