A command for checking whether articles in a local wiki, a collection of linked reference pages, are still up to date. It fetches their sources again, detects changes, and can offer updates for stale articles.

Use it for regular wiki maintenance, source rechecking, stale-article detection, and guided updates.

It reduces the manual work of opening every source and comparing it with the wiki. It also follows configured wiki locations and stops when required access is unavailable instead of silently using the wrong location.

refresh — Command for Claude Code by nvk/llm-wiki

About the project

LLM Wiki is a system that uses AI agents to research sources, compile knowledge bases, organize project briefs, and answer questions from the resulting wiki. It is used to turn rough ideas and investigations into structured, reusable knowledge for agents, including Claude Code, Codex, and OpenCode. The catalogue entries are commands, hooks, skills, instructions, and a plugin that implement its workflow.

nvk/llm-wiki · 1,422 stars · on GitHub · llm-wiki.net

Install

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.

Clone the repo

git clone --depth 1 https://github.com/nvk/llm-wiki

Made for: Claude Code.

Or install wiki, the plugin that ships this one along with the rest of its 1 skill, 28 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nvk/llm-wiki/refresh/github.svg)](https://agentmods.dev/commands/nvk/llm-wiki/refresh)

Your own site

<a href="https://agentmods.dev/commands/nvk/llm-wiki/refresh"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/refresh/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/nvk/llm-wiki/refresh"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/refresh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,941 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00024	$0.01941
Opus 5.5	$0.00010	$0.00776
Sonnet 5.5	$0.00005	$0.00388
Haiku 4.5	$0.00002	$0.00194

Measured 1mo ago against content hash 28933a58a1e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

refresh 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.

claude-plugin/commands/refresh.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Resolve the wiki. Do NOT search the filesystem or read reference files — follow these steps:

Read $HOME/.config/llm-wiki/config.json. If it has hub_path, expand leading ~ only (not tildes in com~apple~CloudDocs) and prefer that path; use resolved_path only as a fallback cache when the expanded hub_path is unavailable and resolved_path is initialized. If config has only resolved_path, use it. If the configured path can be statted but reading wikis.json or listing topics/ fails with Operation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to ~/wiki or resolved_path. Do not write machine-specific resolved_path into shared configs.
If no config → read $HOME/wiki/_index.md. If it exists → HUB = $HOME/wiki. If nothing found, ask the user where to create the wiki.
Wiki location (first match): --local → .wiki/ in CWD; --wiki all → HUB with an ALL_TOPICS flag for step 5; --wiki <name> → HUB/wikis.json lookup with portable path resolution (<HUB>, ~, absolute, or HUB-relative); if the registry path is stale, fall back to HUB/topics/<name>; CWD has .wiki/ → use it; else → HUB.
Read <wiki>/_index.md to verify. If missing → stop with "No wiki found. Run /wiki init first."
Hub-level detection: Refresh operates on articles inside a single topic wiki. The HUB has no wiki/ subdirectory. If ALL_TOPICS is set from --wiki all, read registered topic wikis from HUB/wikis.json (excluding the synthetic hub entry) and iterate refresh against each topic wiki sequentially. If the resolved wiki is the HUB (detected by the presence of wikis.json and the absence of a wiki/ subdir) AND the user did not pass --wiki <name>, do NOT iterate against an empty topic surface. Instead, present a numbered list of registered topic wikis from HUB/wikis.json and ask the user to pick one. Re-resolve the wiki path with the selected name (HUB/topics/<name>/) and continue.

Check whether wiki articles are still current by re-examining their sources. This is NOT automatic recompilation — it's a human-gated assessment of what may have changed.

Inventory awareness: if refresh finds a source that needs later follow-up, monitoring, replacement, or access repair, offer an inventory record or update an existing one. Do not create records for every minor stale article; reserve inventory for durable watch items and blocked actions.

Read the full file on GitHub · 131 lines

Changes

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 · 131 lines · 24 tokens per session scan A 28933a58a1e2

Subscribe to this mod's changes

refresh is a command published in the GitHub repository nvk/llm-wiki (1,422 stars, last pushed 14d ago), licensed MIT. It adds 24 tokens to every session and 1,941 once invoked, about $0.0001 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 2026-08-30.

Claude Code LLM Research agentic-ai agentic-skills agentic-workflow codex

refresh

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Your task

What this file has done since we first saw it

Other commands, from other repositories

orchestrate

agentlas-cloud

agentlas-local

project

export-closedloop-learnings

performance-bottlenecks