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-discover.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-discover)<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-discover"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-discover/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-discover"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-discover.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 | $0.01491 |
| Opus 5 | $0.00000 | $0.00745 |
| Sonnet 5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
wiki-discover 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 today.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover unexpected connections in the LLM Wiki (Memex serendipity).
Usage: /wiki-discover <seed | --random | --surprising | --gaps [<slug>]>
If $ARGUMENTS is empty: print the usage below and stop.
Usage: /wiki-discover <seed | --random | --surprising | --gaps [<slug>]>
Examples:
/wiki-discover Meta # start from a specific entity
/wiki-discover AgenticAI # start from a concept page
/wiki-discover --random # random seed among mid-band backlink hubs
/wiki-discover --surprising # auto-rank top N bridge hubs by composite score
/wiki-discover --gaps # 9-type gap diagnosis + Track A/B/C/D split commentary
/wiki-discover --gaps synthesis # only a specific gap type
gap slug: single-source · stale-hub (A) · bridge (B) · orphan-claims · cap-theme · stale-theme (C) · synthesis · trail · timeline (D).
Traversal Pattern
Reading domain — Meta (graph-traversal tools) + supporting Reporter commentary.
| Cycle | Owner | Action |
|---|---|---|
| Trigger | Editor-in-Chief | slash → mode branch (Mode 1: Seed Discovery / Mode 2: Surprising Bridge Hubs / Mode 3: Gap Inventory) |
| Graph traversal | Meta (tools/discover.py · tools/lint.py graph gaps · wiki/_backlinks.json) |
seed identification · 2-hop exploration · bridge ranking · gap diagnosis |
| Surface | Reporter (mode=ground) | discovered connections + gap commentary |
| (optional) Follow-up | Editor-in-Chief | when the human reviewer has intent, route via re-running the seed · a deeper /wiki-query · /wiki-news --gap · a /wiki-ingest chain (procedure in the ## Follow-up section below) |
Mode 1: Seed Discovery (<seed> or --random)
- Load
wiki/_backlinks.json - Select the seed:
- If a seed argument is given, use that entity/concept
- If
--random, pick a random mid-band hub with backlinks in the 5–30 range
- 2-hop exploration — read the seed page → read the top 5 pages by seed backlinks → identify pages among the common references that are not directly connected to the seed
- Output format:
## 🔍 Discovery: starting from [seed page] ### Unexpected connections 1. **[[PageA]]** ← [1-2 sentences on why it connects] ... ### Suggested explorations - [a question or direction worth digging into deeper]
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.
- today Changed fa6472fde350
- 13d ago First seen · 100 lines · 0 tokens per session scan A 7c3101ad2436
wiki-discover is a command published in the GitHub repository alfadur7/llm-wiki-newsroom (85 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,491 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
migrate
Import existing memory data from another memory plugin into the vault.
prime
Inject preflight context for the current task into the conversation.
recall
Retrieve a specific past session by id or by date range.
mt-recall
Shortcut to the canonical Memtrace decision-memory skill.
tm-save
Save this session's durable memory to trailmem before you exit.
kibi-bootstrap
Bootstrap Kibi knowledge for an existing repository.