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 szaffarano/org-mcp-server --skill org-searchgit clone --depth 1 https://github.com/szaffarano/org-mcp-serverWrote 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/szaffarano/org-mcp-server/org-search)<a href="https://agentmods.dev/skills/szaffarano/org-mcp-server/org-search"><img src="https://agentmods.dev/badge/skills/szaffarano/org-mcp-server/org-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/szaffarano/org-mcp-server/org-search"><img src="https://agentmods.dev/badge/skills/szaffarano/org-mcp-server/org-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.00539 |
| Opus 5.5 | $0.00043 | $0.00216 |
| Sonnet 5.5 | $0.00021 | $0.00108 |
| Haiku 4.5 | $0.00011 | $0.00054 |
Grade A, and why
org-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 2mo 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.
What it actually says
Org Search
Search and browse org-mode documents using the @org MCP server.
Tools
Search — mcp__org__org-search
Fuzzy text search across all org files.
Parameters:
query(required): Search stringtags: Filter results by tagslimit: Max resultssnippet_max_size: Snippet length in chars (default: 100). Use 300+ for more context.
File List — mcp__org__org-file-list
List org files in the configured directory.
Parameters:
tags: Filter by tagslimit: Max files
Resources
Use ReadMcpResourceTool with server: "org" to access file content:
| URI pattern | Use case |
|---|---|
org:// |
List all org files |
org://{file} |
Read full file content |
org-outline://{file} |
Get heading structure (table of contents) |
org-heading://{file}#{heading} |
Read a specific heading's content |
org-id://{uuid} |
Access a node by its unique ID |
Workflow
- Search for content: Use
mcp__org__org-searchwith the user's query. If results are too broad, suggest narrowing with tags or more specific terms. - Browse files: Use
mcp__org__org-file-listto list available files, optionally filtered by tags. - Explore structure: Read
org-outline://{file}to see a file's heading hierarchy before diving in. - Read content: Use
org://{file}for full content ororg-heading://{file}#{heading}to read a specific section. - Present results: Show file name, matched heading, and relevant snippet. Link to deeper content when available.
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.
- 2mo ago First seen · 61 lines · 107 tokens per session scan A ca1834a5b89a
org-search is a skill published in the GitHub repository szaffarano/org-mcp-server (44 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 539 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
agentplaybooks-cli
Audit and synchronize local agent configuration — AGENTS.md / CLAUDE.md instructions, Agent Skills, and MCP server definitions — across Claude Code, Cursor, Codex, Antigravity, Grok Bot, and Hermes with the AgentPlaybooks CLI, and back a project up to or restore it from a hosted playbook. Use only where a terminal…
spec-driven-workflow
Use when starting a non-trivial feature or change — align on WHAT before HOW by recording a proposal, requirement deltas, and a task checklist with the spec tool, then archive to fold the change into the living specs.
session-handoff
Write a short end-of-session handoff covering what changed, what is left, and how to resume. Use when wrapping up a Cursor or Hermes session.
tmux-via-mcp
Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.
tmux-buffer-explorer
Explore large tmux buffers via search and bounded slices. Use when buffer data is too large to load at once or needs incremental inspection.
ai-first-pastebin
Use 呵.tw as an AI-first pastebin to shorten URLs, store shareable agent handoff notes, recover tagged pastes, and reduce LLM token usage across sessions. Trigger this skill when the user wants to: (1) turn long URLs into short links, (2) park long non-secret intermediate output outside the context window, (3) hand off…