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/theexperiencecompany/gaia/accurate-testingnpx skills add theexperiencecompany/gaia --skill accurate-testinggit clone --depth 1 https://github.com/theexperiencecompany/gaiaWhat 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 | $0.00158 | $0.03130 |
| Opus 5 | $0.00079 | $0.01565 |
| Sonnet 5 | $0.00032 | $0.00626 |
| Haiku 4.5 | $0.00016 | $0.00313 |
Grade A, and why
accurate-testing 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
4 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.
- yesterday First seen · 269 lines · 158 tokens per session scan A f01039a91569
accurate-testing is a skill published in the GitHub repository theexperiencecompany/gaia (285 stars, last pushed yesterday), with no licence file. It adds 158 tokens to every session and 3,130 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
olk
Microsoft Outlook and OneDrive CLI and MCP for email, calendar, contacts, tasks, and files, for personal and enterprise accounts.
outlook-mcp
Production-grade MCP server for personal Outlook (Outlook.com / Hotmail / Live). 62 typed Graph tools across mail, calendar, contacts, to-do, drafts, attachments, folders, threading, batch ops, delta-sync. Granular permissions, OS-keyring auth, /$batch-optimized triage and bulk read. Built for agents that need real…
Web research & page automation in Safari (Local MCP)
Use when the user wants to research on the web, pull data from a page, work across their open Safari tabs, or fill in / click through a site. Safari is one of the most-used domains (evaluatejs + navigate→read are top patterns). Powered by Local MCP, driving the user's real Safari.
PDF → spreadsheet — extract data into Excel (Local MCP)
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdfread is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by Local MCP, on-device.
Daily brief / morning catch-up (Local MCP)
Use when the user asks "what's on my plate today", "catch me up", "morning brief", or wants a summary of their day across calendar, reminders and email. The single most common multi-step automation. Powered by Local MCP.
Inbox to action — triage, reply & schedule (Local MCP)
Use when the user wants to deal with their inbox — find what needs a response, draft replies, and turn emails into calendar events or reminders. Captures the common email→read→reply→schedule workflow. Powered by Local MCP.