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/mifunedev/openharness/t3npx skills add mifunedev/openharness --skill t3git clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/mifunedev/openharness/t3)<a href="https://agentmods.dev/skills/mifunedev/openharness/t3"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/t3.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 | $0.00173 | $0.01584 |
| Opus 5 | $0.00086 | $0.00792 |
| Sonnet 5 | $0.00035 | $0.00317 |
| Haiku 4.5 | $0.00017 | $0.00158 |
Grade A, and why
t3 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 today.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
T3 Code
Run T3 Code as a long-running sandbox process: start t3 serve in tmux, report
the pairing URL, and leave the session running. The operator opens it at
localhost:3773 through host/VS Code port forwarding, or — with --tailscale —
from a phone on the same private tailnet.
npx t3 (no subcommand) is the desktop GUI launcher and is not what this skill
runs. Headless and remote access use npx t3 serve; a new device is added to an
already-running server with npx t3 pair.
Arguments
Arguments received: $ARGUMENTS
ACTION: optional first positional argument; defaultstartstart: run the preflight, then startt3 servein tmux, or report the existing sessionstatus: show whether the tmux session is running and print recent outputurl: print the latest pairing URL from the log/pane if presentpair: mint a fresh one-time pairing URL against the running server, without restarting itlogs: print recent log linesstop: kill the tmux sessionattach: print the attach command; do not attach from an agent rundoctor: run the preflight checks and print one actionable line per failurehelp: print script usage
--session: tmux session name; defaultagent-t3code--port: expected T3 Code port; default3773--log: log file; default/tmp/<session>.log--tailscale: publish over Tailscale Serve on the tailnet (t3 serve --tailscale-serve,t3 pair --tailscale)--tailscale-port: alternate Tailscale Serve HTTPS port; default443
If the user does not specify an action, use start.
Preconditions
T3 pairing is not provider auth. Pairing a phone does not log any provider in, and a provider login does not pair a device. They are two separate credentials on two separate lifecycles.
At least one backend must already be installed and authenticated inside the sandbox before T3 Code is useful:
claude # complete OAuth on first launch
codex login
opencode auth login
What ships with it
3 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.
- today Changed · +56 lines · +48 tokens per session 421576c9e016
- 4d ago First seen · 89 lines · 125 tokens per session scan A 5cde798c04e4
t3 is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 173 tokens to every session and 1,584 once invoked, about $0.0009 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
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.