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/escoffier-labs/skillet/t3-codenpx skills add escoffier-labs/skillet --skill t3-codegit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/t3-code)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/t3-code"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/t3-code.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 | $0.00079 | $0.01146 |
| Opus 5 | $0.00039 | $0.00573 |
| Sonnet 5 | $0.00016 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
t3-code 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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
T3 Code
Manage T3 Code without tying the setup to one machine, package source, repository layout, or private network.
Start with the surface
Identify the failing surface before changing anything:
- Desktop application state and launch method.
- T3 server state under the selected base directory.
- Project registration, title, workspace root, or favicon.
- Headless server process or user service.
- Private remote access through Tailscale.
- Update source for the desktop application and CLI.
- Multi-machine topology, saved environments, pairing, or tunnel fallback.
Record the installed version and supported flags first:
t3 --version
t3 project --help
t3 serve --help
Nightly flags and storage details can change. Prefer the installed CLI help over copied commands.
Inspect before changing
- Find the actual executable with
command -v t3. - Identify the configured base directory. The usual default is
~/.t3, but--base-dirorT3CODE_HOMEmay override it. - Determine how the desktop application was installed: package manager, AppImage, source checkout, or another channel.
- Determine whether the server runs interactively, through a wrapper, or as a user service.
- Read
references/multi-machine.mdbefore setting up one desktop to manage projects on other hosts. - Read
references/windows-remote.mdwhen a remote T3 backend runs on Windows. - Read
references/project-state.mdbefore changing project records or icons. - Read
references/remote-tailscale.mdbefore exposing a headless server. - Read
references/updates-and-launchers.mdbefore installing T3 or changing release channels, updates, wrappers, or services.
Prefer supported commands
Use T3 project commands before considering direct database edits:
t3 project add --base-dir "$HOME/.t3" --title "Project (Workstation)" /path/to/repository
t3 project rename --base-dir "$HOME/.t3" /path/to/repository "Project (Workstation)"
t3 project remove --base-dir "$HOME/.t3" /path/to/repository
What ships with it
7 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.
- 6d ago First seen · 106 lines · 79 tokens per session scan A a613ff59410c
t3-code is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 1,146 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 2026-08-31.
Other skills, from other repositories
assess-interview-candidate
根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。.
task-clarifier
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…