What is linkwarden-bookmarks?

Instructions for working with Linkwarden, a tool for saving and organising web links into collections. They describe how to search, save, sort, archive, and delete bookmarks through an MCP server, subject to access scopes.

Finding links, managing collections and tags, processing unread or unsorted bookmarks, checking duplicates, and organising saved pages.

They provide a fixed workflow for handling bookmarks safely and explain which actions are allowed.

linkwarden-bookmarks — Skill for Claude Code and Codex by flumpiey

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.

Any agent

npx skills add flumpiey/linkwarden-mcp --skill linkwarden-bookmarks

Clone the repo

git clone --depth 1 https://github.com/flumpiey/linkwarden-mcp

Made for: Claude Code, Codex.

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/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks/github.svg)](https://agentmods.dev/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks)

Your own site

<a href="https://agentmods.dev/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks"><img src="https://agentmods.dev/badge/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks/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/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks"><img src="https://agentmods.dev/badge/skills/flumpiey/linkwarden-mcp/linkwarden-bookmarks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,392 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	$0.00061	$0.01392
Opus 5	$0.00030	$0.00696
Sonnet 5	$0.00012	$0.00278
Haiku 4.5	$0.00006	$0.00139

Measured 11d ago against content hash 1165e1ad25d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

linkwarden-bookmarks 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 11d 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.

skills/linkwarden-bookmarks/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linkwarden bookmarks

Pairs with the linkwarden-mcp MCP server.

Discovery first

Call list_resources.
Trust its read_only, write_scopes, delete_scopes, effective_write_scopes, and boundary.
Prefer workflow tools (smart_save_link, triage_links, get_sorting_dashboard) over raw field edits when sorting or filing.

Boundary

Empty scopes → read-only tool set (18 tools including list_resources).
Mutations need LINKWARDEN_MCP_WRITE_SCOPES (create/update) and/or LINKWARDEN_MCP_DELETE_SCOPES (delete). Delete is never implied by write.
Recommended write scopes: links,collections (not all domains).
Valid domains: links, collections, tags, plus raw escape hatch.
raw expands effective write scopes to all domain scopes.
Never attempt tokens, session, auth, users (except GET /api/v1/users/me), migration, or whole-instance preservation endpoints.

Config

LINKWARDEN_API_URL — instance base URL (no /api/v1 suffix)
LINKWARDEN_API_KEY — Bearer access token; never echo
Scope CSVs must match between local .env and the MCP host env block
If a tool says Linkwarden is not reachable: tell the user to check URL/key and that the instance is up. Do not treat it as an MCP server crash.

Precondition responses

When a tool returns setup guidance or a structured failure the user must fix:

Relay each item's how_to_create (or equivalent guidance) text to the user verbatim.
Stop. Do not invent a workaround or skip setup steps.

Also stop and relay verbatim for:

Unknown / ambiguous collection or tag names (UnknownNameError / AmbiguousNameError) — list collections/tags first, or use an id.
BulkCapExceeded — shrink the batch or raise LINKWARDEN_MAX_BULK.
Dry-run payloads (dry_run: true) — do not apply until the user confirms dry_run=false.
delete_collection with needs_user_input: true — relay question and options verbatim, ask the user how to dispose of links (delete / move / cancel), then re-call with on_links (and move_to when moving). Do not invent a default disposition.

Read the full file on GitHub · 120 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.

11d ago First seen · 120 lines · 61 tokens per session scan A 1165e1ad25d5

Subscribe to this mod's changes

linkwarden-bookmarks is a skill published in the GitHub repository flumpiey/linkwarden-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 1,392 once invoked, about $0.0003 per session on Opus 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.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

linkwarden-bookmarks