cross-search

cross-search is a skill for Claude Code from Skyfox-io/Memex. It costs 64 tokens per session (672 once invoked), scanned A, original, MIT.

A search across multiple Memex workspaces, where Memex is a system for organizing notes and project context. It searches workspace indexes and summaries rather than opening the individual files.

In plain words
What is it for?
Use it to find mentions of a topic across linked workspaces and identify which workspace or file to open next.
Why use it?
It helps when you know a topic was written somewhere but do not know which workspace contains it.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the memex plugin — 17 skills shipped together

Good fit Use it to find mentions of a topic across linked workspaces and identify which workspace or file to open next.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skyfox-io/memex/cross-search
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 Skyfox-io/Memex --skill cross-search
Clone the repo
git clone --depth 1 https://github.com/Skyfox-io/Memex

Made for: Claude Code.

Or install memex, the plugin that ships this one along with the rest of its 17 skills.

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 cross-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox-io/memex/cross-search.svg)](https://agentmods.dev/skills/skyfox-io/memex/cross-search)
Your own site
<a href="https://agentmods.dev/skills/skyfox-io/memex/cross-search"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/cross-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 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 $0.00064 $0.00672
Opus 5 $0.00032 $0.00336
Sonnet 5 $0.00013 $0.00134
Haiku 4.5 $0.00006 $0.00067

Measured 8d ago against content hash c0003c439836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cross-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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sources.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

memex/skills/cross-search/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wikilink rule: When referencing any file in markdown, always use [[filename]] wikilink format.

Grep across every searchable workspace in ~/.memex/sources.md, grouped by source. Reads only _MANIFEST.md, every _CLOSETS.md, and every _CLOSETS-archive.md. Fast and deterministic.

Registry conventions, script-path resolution, and privacy semantics: see references/registry.md. CLI surface: ${CLAUDE_SKILL_DIR}/scripts/sources.py.

Step 1: Query

Use $ARGUMENTS as the query. If empty, ask: "What do you want to search for across linked workspaces?"

Step 2: Confirm sources exist

python3 "${CLAUDE_SKILL_DIR}/scripts/sources.py" list. If none searchable, tell the user: "No linked workspaces yet. Run /memex:link-workspace from a workspace to register it."

python3 "${CLAUDE_SKILL_DIR}/scripts/sources.py" search "<query>"

The script greps each searchable source's _MANIFEST.md, _CLOSETS.md, and _CLOSETS-archive.md for matches. Results are grouped by source.

Step 4: Format output

If results found:

  1. Show grouped raw results (file path, line, match).
  2. Per source with hits, suggest: "To dive in, switch to that workspace (cd to its path) and start a session."
  3. If a hub by the same name appears across multiple sources, call that out.

If no results:

No matches for "<query>" across <N> linked sources.

Either:
- The subject hasn't been wikilinked into any manifest or closets file.
  /memex:resummarize in the relevant workspace would surface it.
- The subject lives only inside files (not in manifests/closets). Open
  the workspace directly to search inside files.

Gotchas

  • Index-only search. Manifests and closets. Never inside content files. Closets are the index, content is the body. If a subject isn't wikilinked into a closet, it's invisible here. Closets format spec: memex/skills/session-end/references/closets-format.md.
  • searchable: false is total. A source opted out is skipped silently. No partial visibility.
  • Case-insensitive substring. Regex chars in the query are escaped automatically; you can't use regex.
  • Missing path = silent skip per source. If a workspace was moved after linking, cross-search prints (path missing: ...) for that source and continues. Fix with unlink + re-link.

Read the full file on GitHub · 61 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 61 lines · 64 tokens per session scan A c0003c439836

Subscribe to this mod's changes

cross-search is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 672 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 2026-08-30.

Related

Other skills, from other repositories

setup-brain

Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.

mycelium-hq/ai-brain-starter · 66 tokens

second-brain-mapping

Use when the user wants to map or remap their second brain, refresh the vault's queryable metadata index, extract structured frontmatter from typed notes (books, meetings, people, journals, goals), fill wikilink gaps, or surface cross-type insights and patterns no single file shows. Triggers: /second-brain-mapping…

mycelium-hq/ai-brain-starter · 116 tokens

evolve

Use when many related hardened instincts (high-confidence feedback/discovery memories) have piled up in one domain, when the user runs /evolve or asks to promote, cluster, graduate, or consolidate accumulated instincts into a Command, Skill, or Agent, or when files in Instinct Proposals need review. Part of the…

mycelium-hq/ai-brain-starter · 100 tokens

vault-system

Use when maintaining the vault ITSELF as a system, not its content: knowledge-graph build/rebuild/query (graphify), second-brain mapping, vault diagnose/audit/hygiene, drift detection, extract rules from vault, backfill journals, setup vault types, consolidate memory (index over cap), Obsidian tooling…

mycelium-hq/ai-brain-starter · 112 tokens

diagnose

Use when an AI Brain vault needs a health check or something feels off: Claude ignores CLAUDE.md, journal entries missing from /weekly, hooks not firing, something broke after a git pull, a friend's install misbehaves, Obsidian crashes or pegs the CPU, a .claude/worktrees folder appeared, Granola/WhatsApp/Slack/Gmail…

mycelium-hq/ai-brain-starter · 110 tokens

solopreneur-context

When the user wants to set up or update their solopreneur context document — a one-time profile of their business that all other skills reference automatically. Use when the user says "set up my context," "tell you about my business," "save my business info," "update my profile," or when starting a new session and…

Sudhakaran88/solopreneur-skills · 107 tokens