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 sammcj/agentic-coding --skill ghostty-configgit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/sammcj/agentic-coding/ghostty-config)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/ghostty-config"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/ghostty-config/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/sammcj/agentic-coding/ghostty-config"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/ghostty-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 86 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00062 | $0.01580 |
| Opus 5.5 | $0.00025 | $0.00632 |
| Sonnet 5.5 | $0.00012 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
ghostty-config 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ghostty Configuration
Config File Locations
Config is optional; with no file Ghostty runs on its defaults. Since Ghostty 1.2.3 the file is named config.ghostty; extensionless config still loads for backwards compatibility.
- XDG (all platforms):
$XDG_CONFIG_HOME/ghostty/config.ghostty, then$XDG_CONFIG_HOME/ghostty/config.XDG_CONFIG_HOMEdefaults to~/.config. - macOS also:
~/Library/Application Support/com.mitchellh.ghostty/config.ghostty, then.../config.
Every matching file loads, later files overriding earlier ones. Within a location config.ghostty loads before config. On macOS the macOS-path files load after the XDG ones, so macOS paths win on conflict.
Syntax
# Comments start with #
background = 282c34
font-family = "JetBrains Mono"
keybind = ctrl+z=close_surface
font-family = # Empty value resets to default
- Keys are case-sensitive: use lowercase.
- Repeatable keys (
font-family,keybind,palette,env,link) accumulate across lines. - Every config key doubles as a CLI flag:
ghostty --background=282c34 --font-size=14.
Includes
config-file = themes/dark.conf
config-file = ?local.conf # ? prefix = optional, no error if missing
config-file directives are processed at the end of the containing file, so keys written after one still lose to the included file's values. Put overrides in the included file, or include first and keep the parent free of conflicting keys.
Applying Changes
- Reload:
ctrl+shift+,(Linux),cmd+shift+,(macOS). Some options need a restart; some apply only to newly created terminals. - Validate after every edit:
ghostty +validate-config.
CLI Actions
ghostty +<action>; add --help for per-action help.
| Command | Purpose |
|---|---|
ghostty +validate-config |
Check the config for errors |
ghostty +show-config |
Show the effective configuration |
ghostty +show-config --default --docs |
Show defaults with documentation |
ghostty +edit-config |
Open the config in the default editor |
ghostty +list-fonts |
Available fixed-width fonts |
ghostty +list-themes |
Available colour themes |
ghostty +list-colors |
Available X11 colour names |
ghostty +list-keybinds |
Current keybinds (--default for defaults) |
ghostty +list-actions |
All keybind actions |
ghostty +show-face |
Font face information |
ghostty +ssh-cache |
Manage the SSH terminfo cache |
ghostty +new-window |
Open a new window (Linux only) |
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.
- 1mo ago First seen · 115 lines · 62 tokens per session scan A 1534b9fb4862
ghostty-config is a skill published in the GitHub repository sammcj/agentic-coding (165 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,580 once invoked, about $0.0002 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
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
agentpush
Bridge an imported agentpush MCP server (Telegram, WhatsApp, etc.) with live agentproto sessions via the daemon's transmitter subsystem: transmitmessage sends outbound and binds the recipient to a session, inboundwatcherstart polls agentpush for new messages, and inboundendpointcreate/POST /inbound(/:slug) route…
bureau
Drive Bureau — the browser stack's installable capability server: a stealth Firefox (Camofox) + daemon that exposes browser tools as MCP-over-HTTP on :8830, plus a CLI for saved browser identities (sessions), social capture / search, adapter health probes, declarative workflows, and Guilde connection. Use when working…
agentproto-apps
Operate and build Agentproto apps — AIP-53 app bundles (defineApp().emit(dir), APP.md + agents/ + workflows/ + ui/) and their daemon lifecycle (appinstall, appapply, apprun, appstatus, appstop) plus the app-scoped durable data plane (appdataread/write/list/migrate). Covers serving one with a UI (agentproto app serve →…
ap-workflows
Run multi-stage session pipelines with agentproto workflows — workflowstart with barrier-gated stages of concurrent steps, sessionRef to reuse earlier output, workflowstatus/cancel/retry, workflowrunfile for AIP-15 WORKFLOW.md, and workflowescalationresolve for human answers. Trigger when asked to pipeline agents, fan…
Drive the user's authenticated Instagram via the browser skill: profiles, media likers/comments, followers/following, search via the web private API; gated like/comment/follow/DM. Use for Instagram research/outreach as the user.