alcove-capture

alcove-capture is a skill for Claude Code, Codex from OctopusGarage/alcove. It costs 38 tokens per session (963 once invoked), scanned A, original, MIT.

Instructions for capturing web and social-media links into an Alcove inbox, a managed place for reviewing saved knowledge. It also covers reviewing, summarising, archiving, noting, deleting, and deferring captured items.

In plain words
What is it for?
Saving supported social posts and web pages, reviewing captured material, adding notes or summaries, archiving items, deleting them, or postponing review.
Why use it?
It defines a consistent workflow for turning links into complete local records that can be reviewed later, including available images, videos, and OCR text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Saving supported social posts and web pages, reviewing captured material, adding notes or summaries, archiving items, deleting them, or postponing review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/octopusgarage/alcove/alcove-capture
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 OctopusGarage/alcove --skill alcove-capture
Clone the repo
git clone --depth 1 https://github.com/OctopusGarage/alcove

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.

agentmods badge for alcove-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-capture/github.svg)](https://agentmods.dev/skills/octopusgarage/alcove/alcove-capture)
Your own site
<a href="https://agentmods.dev/skills/octopusgarage/alcove/alcove-capture"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-capture/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 alcove-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/octopusgarage/alcove/alcove-capture"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 963 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 $0.00038 $0.00963
Opus 5 $0.00019 $0.00481
Sonnet 5 $0.00008 $0.00193
Haiku 4.5 $0.00004 $0.00096

Measured 11d ago against content hash 196b434e2d0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

alcove-capture 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.

src/alcove/profile_templates/managed-kb/skills/alcove-capture/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alcove Capture

This skill keeps the managed knowledge capture workflow while routing all knowledge behavior through Alcove and all capture behavior through Clipsmith. Clipsmith project page: https://octopusgarage.github.io/clipsmith/

Clipsmith is the default capture adapter, not a hard dependency of Alcove. Other collectors may be used when they write a compatible bundle or folder into this knowledge base's inbox/<platform>/<capture-id>/ path. Alcove reads Clipsmith capture.json.content_files first, so OCR text files declared by Clipsmith are reviewable without a separate Alcove-side OCR step.

If the user sends a supported social-media link, capture the complete post into inbox: full post content, metadata, and all available images/videos. A bare supported social-media link is sufficient authorization for this initial capture; do not ask for additional confirmation. For other downloadable web links, default to capturing the complete article or page into inbox. Do not process unrelated existing inbox items just because a new link was captured.

The captured inbox item must be a complete local bundle. Keep bundle files at the item root and downloaded media under assets/. If the platform is unsupported, login is required, or any content cannot be downloaded, report that explicitly and do not claim the capture is complete.

Expected capture flow:

clipsmith providers --json
clipsmith capture start "<url>" --state-dir /tmp/clipsmith-state
clipsmith validate-bundle "<bundle_dir>" --json
clipsmith capture finalize "<job_id_or_job_path>" "<bundle_dir>" --state-dir /tmp/clipsmith-state
clipsmith sink inbox "<bundle_dir>" . --json

Run the sink command from the managed KB root. If the agent is working from a different directory, replace . with that KB workspace path.

Platform expectations:

  • XiaoHongShu: xhslink.com or xiaohongshu.com/explore/ -> inbox/xhs/
  • X/Twitter: x.com/ or twitter.com/ -> inbox/x/
  • WeChat: mp.weixin.qq.com or weixin.qq.com -> inbox/wechat/
  • Generic web: normal article URLs -> inbox/web/

Read the full file on GitHub · 130 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. 11d ago First seen · 130 lines · 38 tokens per session scan A 196b434e2d0b

Subscribe to this mod's changes

alcove-capture is a skill published in the GitHub repository OctopusGarage/alcove (0 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 963 once invoked, about $0.0002 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

my-wiki

A skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts.

NimaChu/my-wiki · 51 tokens

vault-for-llm

Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.

zycaskevin/Vault-Agent-Memory · 46 tokens

kb-lint

Health check for the PARA Knowledge Base. Detects orphan documents, broken links, index drift, tag issues, and stale content. Run periodically or as part of weekly review.

ernestolee13/para-knowledge-base · 39 tokens

kb

Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…

hraness/kb · 155 tokens

any-mcp

Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.

stevelr/anytype · 68 tokens

grounded-knowledge-workflow

Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…

dimosgit/grounded-knowledge-engine · 91 tokens