session-bookmarks

session-bookmarks is a skill for Claude Code from voxpelli/vp-claude. It costs 129 tokens per session (2,498 once invoked), scanned A, original, MIT.

A skill for finding useful links in the current conversation and saving approved ones as Raindrop bookmarks. Raindrop is a service for organizing web bookmarks.

In plain words
What is it for?
Scanning the session for high-value links, suggesting up to three, and creating and tagging the bookmarks after approval.
Why use it?
It reduces the chance of losing important URLs found during research while leaving the final selection to the user.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the vp-knowledge plugin — 14 skills, 5 agents, 4 hooks shipped together

Good fit Scanning the session for high-value links, suggesting up to three, and creating and tagging the bookmarks after approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/voxpelli/vp-claude/session-bookmarks
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 voxpelli/vp-claude --skill session-bookmarks
Clone the repo
git clone --depth 1 https://github.com/voxpelli/vp-claude

Made for: Claude Code.

Or install vp-knowledge, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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.

agentmods badge for session-bookmarks

README.md
[![agentmods](https://agentmods.dev/badge/skills/voxpelli/vp-claude/session-bookmarks/github.svg)](https://agentmods.dev/skills/voxpelli/vp-claude/session-bookmarks)
Your own site
<a href="https://agentmods.dev/skills/voxpelli/vp-claude/session-bookmarks"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/session-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.

agentmods 80×15 button for session-bookmarks

Your own site · 80×15
<a href="https://agentmods.dev/skills/voxpelli/vp-claude/session-bookmarks"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/session-bookmarks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,498 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.02498
Opus 5 $0.00064 $0.01249
Sonnet 5 $0.00026 $0.00500
Haiku 4.5 $0.00013 $0.00250

Measured 9d ago against content hash d53553917e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

session-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 9d 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/session-bookmarks/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Bookmarks

Scan the current conversation for high-signal URLs discovered during work, suggest 1-3 as Raindrop bookmarks, and create them after user approval.

This skill can be invoked directly or is auto-delegated from /session-reflect after its Basic Memory workflow completes.

Edge Cases

  • No URLs in conversation — exit silently, no output.
  • All candidate URLs already bookmarked — exit silently.
  • Raindrop MCP unavailable — report "Raindrop unavailable — skipping bookmark suggestions" and exit. Do not block the calling skill.
  • create_bookmarks succeeds but update_bookmarks (tags) fails — report partial success: "Bookmark created but tagging failed — add tags manually in Raindrop."
  • User declines all — report "No bookmarks created" and exit.
  • More than 3 candidates pass the filter — take the top 3 by priority: official docs > specs/RFCs > blog posts/tutorials > other.

Signal Detection

A URL is bookmark-worthy when ALL of these criteria are met:

  1. Discovered during the session — via Tavily search, DeepWiki, web fetch, or Claude's own research. NOT a URL the user pasted as the starting point of the conversation. URLs found by following a user-pasted link ARE eligible (the discovery chain matters, not the seed).

  2. Central to a decision or insight — the URL's content was actively used to inform a decision, solve a problem, or confirm an approach. Not just mentioned in passing or returned in a search result that was skipped.

  3. Durable, authoritative content — official documentation, specifications, RFCs, well-written blog posts, research papers, detailed tutorials.

  4. NOT any of these (always skip):

    • Package registry index pages (npmjs.com/package/X, crates.io/crates/X, pypi.org/project/X — these are canonical and already discoverable)
    • GitHub repository root pages (github.com/owner/repo without further path)
    • Localhost or development URLs
    • MCP tool-internal or generated URLs

Read the full file on GitHub · 265 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.

  1. 9d ago First seen · 265 lines · 129 tokens per session scan A d53553917e72

Subscribe to this mod's changes

session-bookmarks is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 11d ago), licensed MIT. It adds 129 tokens to every session and 2,498 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

synergy-tracker

Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…

voxpelli/claude-beads · 197 tokens

upstream-tracker

Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…

voxpelli/claude-beads · 186 tokens

retrospective

Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…

voxpelli/claude-beads · 91 tokens

swarm-wave

Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…

voxpelli/claude-beads · 176 tokens

backlog-groomer

Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…

voxpelli/claude-beads · 191 tokens

harden-memories

Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…

voxpelli/claude-beads · 185 tokens