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.
npx skills add OctopusGarage/alcove --skill notes-searchgit clone --depth 1 https://github.com/OctopusGarage/alcoveWrote 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/notes-search)<a href="https://agentmods.dev/skills/octopusgarage/alcove/notes-search"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/notes-search/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/notes-search"><img src="https://agentmods.dev/badge/skills/octopusgarage/alcove/notes-search.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 | $0.00027 | $0.00568 |
| Opus 5 | $0.00014 | $0.00284 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
notes-search 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alcove Notes Search
This skill is read-only. Use Alcove MCP/CLI search for candidate discovery, then continue with AI-led investigation when the question needs more than direct matches. Do not call retired project-local search scripts.
Routing
- Chinese requests such as
本地个人知识库,知识库,OKF,知识数据,汇总总结,查一下, or相关资料mean Alcove Home-wide search across managed KBs, pins, tasks, prompts, projects, mounts, and connectors unless the user asks to narrow scope. 当前知识库,这个知识库,inbox,archive, or当前目录means this managed KB.- Omit
workspacefor Home-wide MCP search; pass this workspace only for explicit current-KB scope. - Do not route generic
本地知识库wording to unrelated global or project-specific tools unless the user explicitly names that tool.
Investigation Model
- Treat search results as leads, not final truth.
- For broad, ambiguous, cross-topic, or low-confidence questions, inspect OKF indexes, domain/topic/tag pages, candidate records, source refs, connector fetch refs, mount refs, archive provenance, and local files as useful.
- Use the model's reasoning to expand queries, follow relationships, compare records, and synthesize answers from the local evidence found.
- This skill is read-only. Do not mutate files while investigating.
Commands
alcove search "query" --json
alcove search --tags --json
alcove search --recent 20 --json
alcove search --tag <tag> --json
alcove search --topic <domain/topic> --json
alcove search --platform <platform> --json
alcove search --type "Knowledge Concept" --json
alcove search --tag-doctor --json
alcove search --unindexed --json
Search results include type, title, domain, topic, platform, date, published_at,
collected_at, updated_at, deleted_at, tags, confidence, status, resource, and
path. Use these lifecycle fields to decide whether a candidate is outdated.
For user-confirmed cleanup of a specific search result, run
alcove knowledge delete <path> --json first for preview, then rerun with
--confirm only after explicit confirmation. Use archive/ only for
provenance tracing; knowledge/ is the formal knowledge base.
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.
- 10d ago First seen · 56 lines · 27 tokens per session scan A d06641613710
notes-search is a skill published in the GitHub repository OctopusGarage/alcove (0 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 568 once invoked, about $0.0001 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.
Other skills, from other repositories
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
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.
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.
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…
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.
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…