Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OctopusGarage/alcovenpx agentmods add skills/octopusgarage/alcove/alcove-workspaceWrote 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.
[](https://agentmods.dev/skills/octopusgarage/alcove/alcove-workspace)<a href="https://agentmods.dev/skills/octopusgarage/alcove/alcove-workspace"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-workspace/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.
<a href="https://agentmods.dev/skills/octopusgarage/alcove/alcove-workspace"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/alcove-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00813 |
| Opus 5.5 | $0.00011 | $0.00325 |
| Sonnet 5.5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
alcove-workspace 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alcove Business Workspace
This is a lightweight business-scoped Alcove workspace. Read .alcove-workspace.yml first to learn the workspace id, default KB, tags, modules, and purpose.
Operating Model
- Start searches inside this workspace's configured scope: preferred KBs, tags, and modules.
- For workspace-local documents, notes, and recall, use
alcove workspace okf ...before falling back to Home-wide search. - If scoped search is too narrow, say that you are expanding to Home-wide search and then inspect evidence before answering.
- For durable writes, use Alcove CLI/MCP commands and preserve the workspace tag or context from
.alcove-workspace.yml. - Use
workspace okf add-note/import-file/searchfor scene-local knowledge; usepin,task,idea, andprompt recommend/composefor global reusable memory and planning. - If the workspace OKF is not initialized, run
alcove workspace okf init <workspace-id> --jsonbefore saving scene-local knowledge. - Prompt saves must still use the governed propose/save flow; do not turn raw notes or chat fragments into prompts.
- Do not perform Hub-only administration from here by default. Installing entries, editing global MCP, changing services, export/backup, connector/mount administration, radar definitions, publisher configuration, and health fixes belong in the Hub unless the user explicitly authorizes the command.
Workspace Memory Protocol
At the end of a relevant user turn, decide whether the conversation introduced durable workspace memory. Use a mixed policy:
- Auto-save low-risk, explicit, stable facts that belong to this workspace: household or business routines, object locations, care procedures, maintenance notes, recipes, preferences, and long-running non-sensitive todos.
- Ask before saving sensitive, private, ambiguous, or unstable information: medical or veterinary diagnosis and treatment changes, finance and debt, bank cards, identity documents, secrets, other people's private data, unconfirmed plans, and information likely to expire.
- Do not save internal reasoning, transient chat, raw prompts, or speculative conclusions.
- Search workspace OKF first when updating an existing subject. Prefer maintaining a human-readable source file in
documents/and then importing it withworkspace okf import-file --no-copy; useworkspace okf add-notefor small synthesized notes. - Use
taskfor actionable follow-ups and routines that should be tracked,pinonly for tiny durable references, andpromptonly for reviewed reusable instructions. - After saving, return a compact receipt with the title, storage path, classification, tags, and the verification query or command.
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 · 52 lines · 28 tokens per session scan A 031b5dcbd8bc
alcove-workspace is a skill published in the GitHub repository OctopusGarage/alcove (0 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 813 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 2026-08-31.
Other skills, from other repositories
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.
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
wiki-switch
List, create, or switch named Obsidian wiki vault profiles under the global config directory. Use when changing the active vault, checking which vault is active, or managing multi-vault profiles.
knowledge-base-management
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
daily-update
Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder. Use for daily or morning wiki refresh or scheduler setup and verification.
enzyme
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, search by keyword and meaning, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.