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/drolosoft/cmux-resurrect/agentskillnpx skills add drolosoft/cmux-resurrect --skill agentskillgit clone --depth 1 https://github.com/drolosoft/cmux-resurrectWrote 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/drolosoft/cmux-resurrect/agentskill)<a href="https://agentmods.dev/skills/drolosoft/cmux-resurrect/agentskill"><img src="https://agentmods.dev/badge/skills/drolosoft/cmux-resurrect/agentskill.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 | $0.00055 | $0.01256 |
| Opus 5 | $0.00028 | $0.00628 |
| Sonnet 5 | $0.00011 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
crex 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving crex (terminal workspace manager)
crex saves and restores terminal workspaces — tabs, splits, per-pane working directories, running commands — as named layouts, on cmux and Ghostty (auto-detected). It also captures running AI CLI sessions (Claude Code, Codex, OpenCode, and 12 more) and resumes them mid-conversation on restore.
Quick reference
| Task | Command |
|---|---|
| Snapshot current terminal state | crex save <name> -d "why" |
| Restore, keeping what's open | crex restore <name> --mode add |
| Restore, replacing everything | crex restore <name> --mode replace |
| Preview a restore (no changes) | crex restore <name> --dry-run --mode add |
| List saved layouts (JSON) | crex list --json |
| Inspect a layout's contents | crex show <name> (styled) / crex show <name> --raw (TOML) |
| Live workspaces + panes | crex now (human-readable only) |
| New workspace from template | crex template use ide <path> (16 templates: crex template list) |
| Create tabs from a Markdown Blueprint | crex import-from-md [--workspace-file <path>] --dry-run first |
Rules for agents
- Always pass
--modewhen scripting a restore. Without it, crex prompts interactively (replace vs add) and your command hangs.addis non-destructive: it syncs by workspace title — already-open workspaces are skipped, missing ones are created. - Verify the layout exists first — restoring a nonexistent name falls into an interactive picker (hangs scripts). Guard:
crex list --json | jq -e --arg n "NAME" 'map(.name) | index($n)'. JSON fields:name,description,saved_at,workspace_count,workspace_titles,workspace_summaries,file_path. If the name is close-but-wrong, suggest the nearest existing name to the user — never guess. - Preview before mutating:
--dry-runprints the exact backend commands a restore would run, without executing. It does NOT skip the mode prompt — always pair it with--mode. - Snapshot-before-risk pattern:
crex save pre-<task> -d "rollback point"→ do the risky thing → roll back withcrex restore pre-<task> --mode replaceif needed. - Re-saving over an existing name is safe and idempotent. It refreshes the layout from live state, preserves user-edited descriptions and hand-typed commands, and bumps the revision only when content changed. Reuse names freely. There is NO history/undo of previous revisions — if unsure, snapshot to a new name first.
- Never
crex deletewithout explicit user confirmation.
What ships with it
2 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.
- 4d ago First seen · 63 lines · 55 tokens per session scan A 662578b65f5b
crex is a skill published in the GitHub repository drolosoft/cmux-resurrect (80 stars, last pushed 19d ago), licensed MIT. It adds 55 tokens to every session and 1,256 once invoked, about $0.0003 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
corral
Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…
linear-tickets
Use Orca's Linear CLI through orca linear ... commands to read linked ticket context with orca linear issue --current --full --json, post completion updates, move work forward through Linear workflow states, attach PR/MR links with orca linear attach --current --url --title "PR/MR link" --json, and triage Linear tasks…
computer-use
Use Orca's computer-use CLI for OS/window-level inspection and input in visible local app windows. Use when a task must read or operate a native app or an external browser window (for example, Chrome, Edge, or Safari) or an app webview. Do not use for Orca's embedded browser or page-only browser automation. Use…
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
harbor
Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.