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 agentmods add skills/skyfox-io/memex/searchnpx skills add Skyfox-io/Memex --skill searchgit clone --depth 1 https://github.com/Skyfox-io/MemexWrote 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/skyfox-io/memex/search)<a href="https://agentmods.dev/skills/skyfox-io/memex/search"><img src="https://agentmods.dev/badge/skills/skyfox-io/memex/search.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01169 |
| Opus 5 | $0.00026 | $0.00584 |
| Sonnet 5 | $0.00011 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memex - Search
Wikilink rule: When referencing files in any markdown you write, use [[filename]] format.
Cross-hub search within the current workspace. Same retrieval surface as /memex:cross-search, scoped to one workspace.
Step 1: Resolve workspace and query
Run WORKSPACE_ROOT=$(pwd) && echo "$WORKSPACE_ROOT" via Bash.
Use $ARGUMENTS as the query. If empty, ask: "What do you want to search for across hubs in this workspace?"
If _MANIFEST.md is missing, tell the user "Memex isn't initialized in this workspace. Run /memex:init first." and stop.
Step 2: Search
Run ${CLAUDE_SKILL_DIR}/scripts/sources.py:
python3 "${CLAUDE_SKILL_DIR}/scripts/sources.py" search-local "<query>" --workspace "$WORKSPACE_ROOT"
The script greps _MANIFEST.md, every _CLOSETS.md and _CLOSETS-archive.md, and memory/.graph.md under the workspace. Output is grouped by folder.
Step 2b: Similarity supplement (built-in)
Always run this after grep, never instead of it:
python3 "${CLAUDE_SKILL_DIR}/scripts/semantic.py" query "<query>" --workspace "$WORKSPACE_ROOT"
Show hits under a Similarity matches section placed AFTER the grep results. Dedupe against grep hits: skip any result whose stem grep already surfaced.
Step 3: Format output
If results found:
- Show the script's grouped output verbatim (folder header, file:line:match lines).
- Summarize what cuts across hubs: if the same query hits multiple hub folders, call that out — that's the cross-hub signal the user came for.
- If a hit is in the Recently Archived section of a
_CLOSETS.md, suggest loading the corresponding_CLOSETS-archive.mdfor full typed-field context on that file.
If no results (grep and Step 2b's similarity pass both found nothing):
No matches for "<query>" in this workspace.
Either:
- The subject isn't wikilinked into the manifest or any closets file.
Run /memex:resummarize or /memex:reindex to refresh closets.
- The subject lives only inside content files. Open the relevant hub's
files directly (closets surface what's *in* the index, not raw content).
- The similarity pass (Step 2b) also found nothing — the subject likely
isn't indexed; run /memex:reindex.
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.
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.
- 5d ago First seen · 86 lines · 53 tokens per session scan A 3745915e235c
search is a skill published in the GitHub repository Skyfox-io/Memex (17 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,169 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.
Other skills, from other repositories
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…
obsidian-companion
Use when interacting with the user's Obsidian vault — reading, writing, searching, or chatting with notes using local RAG. Guides tool selection and writing strategy for all vault operations.
wiki-ingest
Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".
vault-lint
Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps. Triggers on "lint vault", "vault health", "check vault", "stale notes", "vault audit", "vault quality", or "check conventions".
compound
Use when the user wants to promote cross-project knowledge to the global Engineering/ folder, or says "promote knowledge", "compound notes", "knowledge synthesis", or "find repeated ideas across projects".
links
Use when the user wants to explore connections between notes, see what links to or from a note, or says "links", "backlinks", "connections", or "graph".