A lifecycle tool for topic wikis that moves old topics into an archive while preserving them. Archived topics are hidden from normal wiki searches and maintenance work.

Use it to archive or restore whole topic wikis and keep the main wiki focused on current subjects.

It keeps inactive interests out of everyday context without deleting their files. Archived topics can still be restored or maintained explicitly.

archive — 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 · 1,467 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/archive/github.svg)](https://agentmods.dev/commands/nvk/llm-wiki/archive)

Your own site

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

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,576 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	$0.00036	$0.01576
Opus 5.5	$0.00014	$0.00630
Sonnet 5.5	$0.00007	$0.00315
Haiku 4.5	$0.00004	$0.00158

Measured 1mo ago against content hash c6255bd32800, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

archive 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/archive.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Manage the archive lifecycle for topic wikis. Archive is a context filter, not deletion: preserve the wiki, remove it from normal semantic workflows, and keep explicit restore/maintenance possible.

Read skills/wiki-manager/references/archive.md, skills/wiki-manager/references/hub-resolution.md, and skills/wiki-manager/references/wiki-structure.md before mutating files.

Resolve HUB

Archive is a hub-level operation. Resolve HUB with the standard protocol:

Read $HOME/.config/llm-wiki/config.json. Prefer hub_path, expanding only a leading ~. Use resolved_path only as the legacy fallback described in hub-resolution.md.
If no config exists, try $HOME/wiki/_index.md.
Verify HUB/wikis.json and HUB/topics/ exist, unless the subcommand is helping initialize/report an empty hub.
If the path can be statted but reading wikis.json or listing topics/ fails with Operation not permitted, stop with the hub-resolution diagnostic and do not fall back to another path.

Do not archive project-local .wiki/ directories in v1. Project archive remains /wiki:project archive; inventory and dataset archive remain status: archived.

Parse $ARGUMENTS

Subcommands:

list: show active topic wikis and archived counts. With --archived, show archived topics in a separate table.
topic : archive an active topic wiki.
restore : restore an archived topic wiki to active status.
peek : search archived topic indexes only and report possible matches without reading archived articles.

Flags:

--reason "why": optional archive reason stored in wikis.json.
--archived: include archived topics in list output.
--include-archived: allow explicit archived reads for peek or when a routed query follows an archived match.

If the input is empty, show the subcommands and examples.

Archive Topic

For topic <slug>:

Refuse slug = hub.
Read HUB/wikis.json.
Resolve the active topic path:
- Prefer a registry entry whose status is not archived.
- Resolve registry paths as <HUB>, ~, absolute, or HUB-relative.
- If the registry is stale but HUB/topics/<slug>/_index.md exists, use it and repair the registry.
Fail if the source wiki is missing or already archived.
Fail if HUB/topics/.archive/<slug>/ already exists.
mkdir -p HUB/topics/.archive
Move HUB/topics/<slug> to HUB/topics/.archive/<slug>.
Update wikis.json:
- path: "topics/.archive/<slug>"
- status: "archived"
- archived: YYYY-MM-DD
- archive_reason: "<reason>" when provided
Regenerate the hub _index.md active-topic table so archived topics do not appear as active. Include an archived count.
Append logs:

HUB/log.md: ## [YYYY-MM-DD] archive | archived topic <slug>
archived topic log.md: same entry, if writable.

Report the old path, new path, and restore command.

Read the full file on GitHub · 159 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 · 159 lines · 36 tokens per session scan A c6255bd32800

Subscribe to this mod's changes

archive is a command published in the GitHub repository nvk/llm-wiki (1,467 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,576 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 Memory and context agentic-ai agentic-skills agentic-workflow codex

archive

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

Resolve HUB

Parse $ARGUMENTS

Archive Topic

What this file has done since we first saw it

Other commands, from other repositories

hive-mind-memory

ask

help

debug

rem_help

export-closedloop-learnings