What is headsup-config?

A single settings command for Headsup, a tool that changes Claude Code and Codex terminal-tab behavior on macOS.

Use it to configure new tabs, tab colors, titles and badges, and waiting-tab notifications.

It puts tab launch modes, colors, labels, and notifications behind one entry point instead of separate commands.

headsup-config — Skill for Claude Code and Codex by wasulajr/headsup

Install

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.

Any agent

npx skills add wasulajr/headsup --skill headsup-config

Clone the repo

git clone --depth 1 https://github.com/wasulajr/headsup

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wasulajr/headsup/headsup-config/github.svg)](https://agentmods.dev/skills/wasulajr/headsup/headsup-config)

Your own site

<a href="https://agentmods.dev/skills/wasulajr/headsup/headsup-config"><img src="https://agentmods.dev/badge/skills/wasulajr/headsup/headsup-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wasulajr/headsup/headsup-config"><img src="https://agentmods.dev/badge/skills/wasulajr/headsup/headsup-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,314 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00153	$0.01314
Opus 5.5	$0.00061	$0.00526
Sonnet 5.5	$0.00031	$0.00263
Haiku 4.5	$0.00015	$0.00131

Measured 2mo ago against content hash c8c5425c6a77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

headsup-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 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.

skills/headsup-config/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/headsup-config: headsup settings hub

One entry point for every headsup setting. The first word of the arguments selects a section; the rest is that section's own arguments, passed straight through to the same backing helper the dedicated skill uses. The focused skills (/headsup-colors, /headsup-label, /headsup-notifications) still exist and auto-trigger on natural phrasing; this is the unified manual entry point, and it is the ONLY skill for the New Claude Tab launch mode (there is no separate /headsup-newtab-args).

Sections

Section	What it sets	Backing helper
`newtabs`	New Claude Tab (Cmd-Opt-C) launch mode	`~/.claude/hooks/headsup-newtab-args.sh`
`codextabs`	New Codex Tab launch mode	`~/.claude/hooks/headsup-newtab-args.sh --codex`
`colors`	idle / processing / waiting tab colors (global)	the `/headsup-colors` procedure
`label`	this tab's title + badge (per-session)	`~/.claude/hooks/headsup-set-label.sh`
`notify`	the "Claude is waiting" macOS notification	`~/.claude/hooks/headsup-notifications.sh`

Accepted section aliases: newtab/autorun -> newtabs; codex/codextab -> codextabs; color -> colors; title/badge -> label; notifications -> notify.

What to do when invoked

Parse the arguments. The first whitespace-delimited token is the section; everything after it is rest (may be empty). Map aliases to a canonical section above.
No section, or show / status / help: show every current setting, then stop. Run these (read-only) and summarize the output:
```
~/.claude/hooks/headsup-newtab-args.sh --show
~/.claude/hooks/headsup-newtab-args.sh --codex --show
~/.claude/hooks/headsup-notifications.sh            # prints current notify state
grep -E '^(IDLE|PROCESS|WAIT)_COLOR=' ~/.claude/hooks/headsup-status.conf
```
Also note the current per-session label is whatever /headsup-label last set (mention it is per-tab). List the sections so the user knows what they can change.

Read the full file on GitHub · 68 lines

Changes

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 · 68 lines · 153 tokens per session scan A c8c5425c6a77

Subscribe to this mod's changes

headsup-config is a skill published in the GitHub repository wasulajr/headsup (1 stars, last pushed 9d ago), licensed MIT. It adds 153 tokens to every session and 1,314 once invoked, about $0.0006 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 2026-08-31.

Claude Code Productivity claude-code-hooks claude-code-skills claude-skills developer-tools iterm2

headsup-config next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
headsup-configwasulajr/headsup	Skill	1	9d ago	MIT	A	153	Claude Code, Codex
chief-of-staffalirezarezvani/claude-skills	Skill	29k	yesterday	MIT	A	43	Claude Code
founder-coachalirezarezvani/claude-skills	Skill	29k	yesterday	MIT	A	41	Claude Code
cs-onboardalirezarezvani/claude-skills	Skill	29k	yesterday	MIT	A	47	Claude Code
setupme2resh/apexyard	Skill	542	yesterday	MIT	A	26	Claude Code
mix-compressionoliver-kriska/claude-elixir-phoenix	Skill	574	yesterday	MIT	A	48	Claude Code
phx-mix-compressionoliver-kriska/claude-elixir-phoenix	Skill	574	yesterday	MIT	A	51	Claude Code