nil

A command that reopens saved terminal work sessions, restoring selected windows or tabs for Codex or Claude.

In plain words
What is it for?
Resuming saved sessions in iTerm2, WezTerm, or AI Power Term, choosing which sessions to reopen, and continuing with the current coding agent.
Why use it?
It removes the need to find and restart previously saved projects manually across supported macOS terminals.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/wasulajr/headsup/nil
Any agent
npx skills add wasulajr/headsup --skill nil
Clone the repo
git clone --depth 1 https://github.com/wasulajr/headsup

Made for: Claude Code, Codex.

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00153 $0.02183
Opus 5 $0.00077 $0.01092
Sonnet 5 $0.00031 $0.00437
Haiku 4.5 $0.00015 $0.00218

Measured 2d ago against content hash e440ca31ab74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nil 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 2d 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/nil/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/nil: now is later

The inverse of /sfl. Where sfl saved each window for later, /nil says later is now: it reopens them. You choose which to bring back.

Requirements

  • macOS with iTerm2, WezTerm, or AI Power Term. The opener chooses the current terminal provider automatically: AI_POWER_TERM_SESSION_ID means AI Power Term; WEZTERM_PANE means WezTerm; ITERM_SESSION_ID means iTerm2; outside those, legacy iTerm2 remains the default. Force AI Power Term with HEADSUP_NIL_PROVIDER=ai-power-term.
  • Claude or Codex on the login-shell PATH. The opener chooses the current agent automatically: Codex when run from Codex, otherwise Claude. Force an agent with HEADSUP_NIL_AGENT=codex|claude.
  • For iTerm2: macOS Automation permission for controlling iTerm2. The first run triggers a prompt; allow it. If denied later, re-enable under System Settings > Privacy & Security > Automation.
  • For WezTerm: the wezterm CLI must be available. The normal install path/symlink is enough.
  • Current-agent resume. Each new tab runs cd ... && <label helper> ... && <agent> <resume prompt>. Claude resumes restore Claude permission mode from the saved entry; Codex resumes use normal Codex local config and approval policy.

What it does

For each selected live checkpoint in ~/.claude/sfl/*.md (one per saved window), open a new tab in the current provider that:

  1. cds into the window's recorded cwd,
  2. restores the window's headsup label via headsup-set-label.sh (iTerm2 badge/title or WezTerm label/user vars),
  3. launches the current/forced agent CLI with a resume prompt pointing at that window's archived entry file. Claude launches in the saved permission mode (--permission-mode <mode> from the entry's mode: field: auto-accept / plan / default / bypass). Codex launches with normal Codex config.

/nil archives only the LAUNCHED entries, at launch time. nil-open.sh moves each selected entry into ~/.claude/sfl/archive/ before the tabs open and points its resume prompt at the archived path, so a launched window can never be relaunched twice by a later /nil. Un-selected entries stay live in ~/.claude/sfl/, so you can bring them back with a later /nil. If launch fails, the script rolls back entries that were not successfully launched. Each reopened tab then self-resumes: its claude runs /sfl resume mode, reads the archived entry plus its gov_memory reference, and gives a 3-5 line catch-up; it does NOT need to archive anything.

Read the full file on GitHub · 83 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.

  1. 2d ago First seen · 83 lines · 153 tokens per session scan A e440ca31ab74

Subscribe to this mod's changes

nil is a skill published in the GitHub repository wasulajr/headsup (1 stars, last pushed 15d ago), licensed MIT. It adds 153 tokens to every session and 2,183 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 2026-08-31.

Related

Other skills, from other repositories

add-office365

Adds Office 365 Outlook connector to a Power Apps code app. Use when accessing calendars, sending emails, reading inbox, or managing Outlook events.

microsoft/power-platform-skills · 33 tokens

idea

Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT…

serejaris/personal-corp-os · 135 tokens

os-step-by-step

ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do"…

kharmanskyi/open-steps · 180 tokens

os-done-or-not

ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what happened", "report" - in any language, and when a Stop hook asks for a session report. Produces a ten-line plain- language report: a lead, a checkmark table, and a verdict - fully done, anything needed from…

kharmanskyi/open-steps · 127 tokens

clean-downloads

Propose and execute a cleanup of the user's Downloads folder — sort into subfolders by type and age, flag duplicates and large files. Always plan first, never delete. Use when the user runs /clean-downloads.

AlpacaLabsLLC/skills-for-architects · 48 tokens

meeting-transcription

Transcribe meeting audio with speaker diarization, generate structured summaries with action items, decisions, and follow-ups, and support multiple audio formats and languages. Use when the user requests meeting transcription or provides relevant inputs for this workflow.

seb1n/awesome-ai-agent-skills · 49 tokens