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 danielsimonjr/everything-mcp --skill everythinggit clone --depth 1 https://github.com/danielsimonjr/everything-mcpWrote 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/danielsimonjr/everything-mcp/everything)<a href="https://agentmods.dev/skills/danielsimonjr/everything-mcp/everything"><img src="https://agentmods.dev/badge/skills/danielsimonjr/everything-mcp/everything.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 5.1 | $0.00080 | $0.00714 |
| Opus 5 | $0.00040 | $0.00357 |
| Sonnet 5 | $0.00016 | $0.00143 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
everything 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.
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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Everything
A judgment layer over the everything-mcp server's 2 tools — instant, index-backed file/folder lookup on Windows, wrapping voidtools' Everything engine via its es.exe CLI. This skill adds no tools of its own: every action below is one of the server's existing MCP tools. Its job is to steer you toward search for name/pattern lookups, get_file_info for details on a known path, and to flag the one gotcha that actually bites on this machine — an index gap for Dropbox.
Skill root: this skill ships inside the everything-mcp plugin (repo danielsimonjr/everything-mcp, skills/everything/). Slash trigger: /everything.
The two tools
| Tool | Purpose |
|---|---|
search |
Search files/folders by Everything syntax — wildcards (*.js), boolean (file AND doc, NOT backup), extensions (ext:jpg;png), size (size:>1mb), dates (dm:today), path (path:C:\Users\, parent:Downloads), regex. Instant because it queries Everything's live index, not the filesystem. |
get_file_info |
Given a full path or filename, returns size, creation/modified/accessed dates, and attributes. |
Reach for search whenever the ask is "find/locate/where is a file matching X" — it's instant across the whole indexed drive set, no directory walk needed. Reach for get_file_info once you already have a candidate path and need its details rather than more candidates.
If a tool isn't loaded, fetch its schema first: ToolSearch select:mcp__plugin_everything-mcp_everything-mcp__search.
Gotcha: Everything does NOT index ~\Dropbox on this machine
Observed on this machine: Everything's index excludes C:\Users\danie\Dropbox (the reason for the exclusion wasn't investigated — only the observed behavior). A search call scoped to or containing Dropbox paths will silently miss files that exist there. For any Dropbox-rooted search, don't trust search — fall back to a direct filesystem walk (Get-ChildItem -Recurse via PowerShell, or the fzf-mcp server's fuzzy_search_files) instead of assuming absence from an empty search result.
What ships with it
1 file 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.
- 8d ago First seen · 30 lines · 80 tokens per session scan A 5d7f19c61095
everything is a skill published in the GitHub repository danielsimonjr/everything-mcp (12 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 714 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.