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 skills add po4yka/llm-wiki-skills --skill llm-wiki-news-radargit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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/skills/po4yka/llm-wiki-skills/llm-wiki-news-radar)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-news-radar"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-news-radar/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/skills/po4yka/llm-wiki-skills/llm-wiki-news-radar"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-news-radar.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 | $0.00074 | $0.01197 |
| Opus 5.5 | $0.00030 | $0.00479 |
| Sonnet 5.5 | $0.00015 | $0.00239 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
llm-wiki-news-radar 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki News Radar
Goal
Produce a current, source-cited ecosystem update for LLM-Wiki and adjacent technologies.
When to use
- The user asks about the latest, current, or recent state of LLM-Wiki, wiki memory, Agent Skills, RAG/GraphRAG, or related coding-agent knowledge tooling.
- The user asks "what changed" in these areas since a specific date or event.
- The user wants a source-cited digest of new releases, papers, tools, or standards before adopting them.
- Not for general questions that do not need freshness checking (use a vault-query skill instead).
Mandatory freshness rule
Always browse. Do not answer current-state questions from memory.
Use absolute dates in the answer, especially when the user says latest, recent, today, this week, this month or current.
Watch areas
Search across:
- LLM-Wiki / wiki memory / OpenWiki;
- LangChain, DeepAgents and related wiki-memory projects;
- Karpathy-style LLM-Wiki discussions;
- Agent Skills, skills.sh, Claude Code, Codex, Cursor, OpenCode;
- Obsidian/local-first knowledge workflows;
- qmd or local hybrid retrieval;
- RAG, GraphRAG, LightRAG, HippoRAG and agent-native retrieval;
- provenance, anti-slop, context poisoning, memory benchmarks;
- arXiv papers and benchmark releases;
- GitHub repos and release notes.
Inputs
- The topic or watch area(s) to focus the search on; defaults to the full watch-area list above.
- The time window to cover (last 7 days, last 30 days, last 90 days, since a known event, or general landscape); infer or ask if not given.
- Optional: an LLM-Wiki vault path, if the result should be saved via the file-back step.
Procedure
1. Set the time window
Infer or ask for the window:
- last 7 days;
- last 30 days;
- last 90 days;
- since a known event;
- general current landscape.
If no window is given, default to the last 90 days plus any major still-relevant baseline sources.
2. Search diverse sources
Use at least three source families when possible:
- official docs/blogs/release notes;
- GitHub repositories/releases/issues;
- papers/preprints;
- independent analysis or community discussions.
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.
- 1mo ago First seen · 149 lines · 74 tokens per session scan A f706aae2b95e
llm-wiki-news-radar is a skill published in the GitHub repository po4yka/llm-wiki-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,197 once invoked, about $0.0003 per session on Opus 5.5. 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
obsidian-memory
Explicit-only Obsidian memory workflow. Use when the user explicitly asks to work with an Obsidian vault, LLM wiki, agent memory, RAW/source ingest, provenance, QUERY, LINT, or release safety for a markdown knowledge system. Do not auto-route ordinary coding sessions into external vault workflows.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.